Research Methods for Business Students 7e by Saunders, Lewis, Thornhill

Research Methods for Business Students 7e by Saunders, Lewis, Thornhill is the 7th edition of the textbook authored and copyrighted by Mark Saunders, Philip Lewis, and Adrian Thornhill and published in 2016 by Pearson Education Limited, Harlow, Essex, England and associated companies throughout the world.

• 50th percentile. The middle value when all the values of a variable are arranged in rank order; usually known as the median.
• Abductive approach. Approach to theory development involving the collection of data to explore a phenomenon, identify themes and explain patterns, to generate a new – or modify an existing – theory which is subsequently tested.
• Abstract. (1) Summary, usually of an article or book, which also contains sufficient information for the original to be located. (2) Summary of the complete content of the project report.
• Access. (1) The process involved in gaining entry into an organisation to undertake research. (2) The situation where a research participant is willing to share data with a researcher. See also cognitive access, continuing access, physical access.
• Action Research. Research strategy concerned with the management of a change and involving close collaboration between practitioners and researchers. The results flowing from Action Research should also inform other contexts.
• Active response rate. The total number of responses divided by the total number in the sample after ineligible and unreachable respondents have been excluded. See ineligible respondent, unreachable respondent. See also break off, complete response, complete refusal, partial response total response rate.
• Active voice. The voice in which the action of the verb is attributed to the person. For example, 'I conducted interviews'.
• Ad hoc survey. A general term normally used to describe the collection of data that only occurs once due to the specificity of focus. Although the term is normally interpreted as referring to questionnaires, it also includes other techniques such as structured observation and structured interviews. See also survey.
• Alpha coefficient see. Cronbach's alpha.
• Alternative hypothesis. Testable proposition stating that there is a difference or relationship between two or more variables. Often referred to as Ha. See also hypothesis, null hypothesis.
• Analysis. The ability to break down data and to clarify the nature of the component parts and the relationship between them.
• Analysis of variance. Statistical test to determine the probability (likelihood) that the values of a numerical data variable for three or more independent samples or groups are different. The test assesses the likelihood of any difference between these groups occurring by chance alone.
• Analytic induction. Analysis of qualitative data that involves the iterative examination of a number of strategically selected cases to identify the cause of a particular phenomenon.
• Anonymity. (1) The process of concealing the identity of participants in all documents resulting from the research. (2) The promise that even the researcher will not be able to identify by whom responses are made.
• ANOVA. See analysis of variance.
• Appendix. A supplement to the project report. It should not normally include material that is essential for the understanding of the report itself, but additional relevant material in which the reader may be interested.
• Application. The ability to apply certain principles and rules in particular situations.
• Applied research. Research of direct and immediate relevance to practitioners that addresses issues they see as important and is presented in ways they can understand and act upon.
• Archival research. Research strategy that analyses administrative records and documents as principal sources of data because they are products of day-to-day activities.
• Asynchronous. Not undertaken in real time, working offline.
• Attitude variable. Variable that records data about what respondents feel about something.
• Autocorrelation. The extent to which the value of a variable at a particular time (t) is related to its value at the previous time period (t - 1).
• Availability sampling. See convenience sampling.
• Axial coding. The process of recognising relationships between categories in grounded theory.
• Axiology. A branch of philosophy concerned with the role of values and ethics within the research process.
• Bar graph/chart. Graph for showing frequency distributions for a categorical or grouped discrete data variable, which highlights the highest and lowest values.
• Base period. The period against which index numbers are calculated to facilitate comparisons of trends or changes over time. See also index number.
• Basic research. Research undertaken purely to understand processes and their outcomes, predominantly in universities as a result of an academic agenda, for which the key consumer is the academic community.
• Behaviour variable. Variable that records data about behaviours, what people did in the past, do now or will do in the future.
• Beneficence. Actions designed to promote beneficial effects. See also code of ethics.
• Between-subjects design. Experimental design allowing a comparison of results to be made between an experimental group and a control group. See also experiment, within-subjects design.
• Bibliographic details. The information needed to enable readers to find original items consulted or used for a research project. These normally include the author, date of publication, title of article, title of book or journal.
• Bibliography. Alphabetical list of the bibliographic details for all relevant items consulted and used, including those items not referred to directly in the text. The university will specify the format of these.
• Big data. Extremely large and complex (socio-economic) data sets that are analysed by powerful computer techniques to reveal patterns and trends.
• Blog. A personal online journal on which an individual or group of individuals record opinions, information and the like on a regular basis for public consumption. Most blogs are interactive allowing visitors to leave comments. 'Blog' is an abbreviation of 'weblog'.
• Boolean logic. System by which the variety of items found in a search based on logical propositions that can be either true or false can be combined, limited or widened.
• Box plot. Diagram that provides a pictorial representation of the distribution of the data for a variable and statistics such as median, inter-quartile range, and the highest and lowest values.
• Brainstorming. Technique that can be used to generate and refine research ideas. It is best undertaken with a group of people.
• Break off. The level of response to questionnaires or structured interviews in which less than 50% of all questions answered other than by a refusal or no answer. Break off therefore includes complete refusal.
• Broker. See gatekeeper.
• CAQDAS. Computer-Aided Qualitative Data Analysis Software.
• Case. (1) Individual element or group member within a sample or population such as an employee. (2) Individual unit for which data have been collected.
• Case study. Research strategy that involves the empirical investigation of a particular contemporary phenomenon within its real-life context, using multiple sources of evidence.
• Categorical data. Data whose values cannot be measured numerically but can either be classified into sets (categories) or placed in rank order.
• Categorising. The process of developing categories and subsequently attaching these categories to meaningful units of data. See also unitising, units of data.
• Category question. Closed question in which the respondent is offered a set of mutually exclusive categories and instructed to select one.
• Causality. Relationship between cause and effect. Everything that happens will have a cause, while each action will cause an effect.
• Causal relationship. Relationship between two or more variables in which the change (effect) in one variable is caused by the other variable(s).
• Census. The collection and analysis of data from every possible case or group member in a population.
• Central limit theorem. The larger the absolute size of a sample, the more closely its distribution will be to the normal distribution. See normal distribution.
• Central tendency measure. The generic term for statistics that can be used to provide an impression of those values for a variable that are common, middling or average.
• Chat room. An online forum operating in synchronous mode. See also synchronous.
• Chi square test. Statistical test to determine the probability (likelihood) that two categorical data variables are independent. A common use is to discover whether there are statistically significant associations between the observed frequencies and the expected frequencies of two variables presented in a cross-tabulation.
• Classic experiment. Experiment in which two groups are established and members assigned at random to each. See also experiment, experimental group.
• Closed question. Question that provides a number of alternative answers from which the respondent is instructed to choose.
• Cluster sampling. Probability sampling procedure in which the population is divided into discrete groups or clusters prior to sampling. A random sample (systematic or simple) of these clusters is then drawn.
• Code. (1) A single word or short phrase, sometimes abbreviated, used to label a unit of data. (2) a number or word used to represent a response by a respondent or participant. See also coding, codebook, coding template unit of data.
• Code of ethics. Statement of principles and procedures for the design and conduct of research. See also privacy, research ethics, research ethics committee.
• Codebook. Complete list of all the codes used to code data variables.
• Coding. The process of labelling of data using a code that symbolises or summarises the meaning of that data. See also axial coding, categorising, data code, focused coding, initial coding, open coding, selective coding, unitizing, unit of data.
• Coding template. An hierarchical list of codes and themes, which is used as the central analytical tool in Template Analysis. See also Template Analysis.
• Coefficient of determination. Number between 0 and 1 that enables the strength of the relationship between a numerical dependent variable and a numerical independent variable to be assessed. The coefficient represents the proportion of the variation in the dependent variable that can be explained statistically by the independent variable. A value of 1 means that all the variation in the dependent variable can be explained statistically by the independent variable. A value of 0 means that none of the variation in the dependent variable can be explained by the independent variable. See also regression analysis.
• Coefficient of multiple determination. Number between 0 and 1 that enables the strength of the relationship between a numerical dependent variable and two or more numerical independent variables to be assessed. The coefficient represents the proportion of the variation in the dependent variable that can be explained statistically by the independent variables. A value of 1 means that all the variation in the dependent variable can be explained statistically by the independent variables. A value of 0 means that none of the variation in the dependent variable can be explained by the independent variables. See also multiple regression analysis.
• Coefficient of variation. Statistic that compares the extent of spread of data values around the mean between two or more variables containing numerical data.
• Cognitive access. The process of gaining access to data from intended participants. This involves participants agreeing to be interviewed or observed, within agreed limits. See also informed consent.
• Cohort study. Study that collects data from the same cases over time using a series of 'snapshots'.
• Collinearity. The extent to which two or more independent variables are correlated with each other. Also termed multicollinearity.
• Comparative proportional pie chart. Diagram for comparing both proportions and totals for all types of data variables.
• Compiled data. Data that have been processed, such as through some form of selection or summarising.
• Complete observer. Observational role in which the researcher does not reveal the purpose of the research activity to those being observed. However, unlike the complete participant role, the researcher does not take part in the activities of the group being studied.
• Complete participant. Observational role in which the researcher attempts to become a member of the group in which research is being conducted. The true purpose of the research is not revealed to the group members.
• Complete refusal. The level of response to questionnaires or structured interviews in which none of the questions are answered.
• Complete response. The level of response to questionnaires or structured interviews in which over 80% of all questions answered other than by a refusal or no answer.
• Computer-aided personal interviewing (CAPI). Type of interviewing in which the interviewer reads questions from a computer screen and enters the respondent's answers directly into the computer.
• Computer-aided telephone interviewing (CATI). Type of telephone interviewing in which the interviewer reads questions from a computer screen and enters the respondent's answers directly into the computer.
• Conclusion. The section of the project report in which judgements are made rather than just facts reported. Newmaterial is not normally introduced in the conclusion.
• Concurrent embedded design. Mixed-methods research design where the collection of either quantitative or qualitative data is embedded within the collection of the other. See also concurrent mixed-methods research, embedded mixed methods research.
• Concurrent mixed-methods research. Research using both quantitative and qualitative methods that are conducted concurrently during a single phase of data collection and analysis.
• Concurrent triangulation design. Mixed-methods research design where quantitative and qualitative data are collected in the same phase so that these data can be compared to see where they converge or diverge in relation to addressing your research question.
• Confidentiality. (1) Concern relating to the right of access to the data provided by the participants and, in particular the need to keep these data secret or private.(2)Promise made by the researcher not to reveal the identity of participants or present findings in a way that enables participants to be identified.
• Confounding variables. Extraneous but difficult to observe or measure variables than can potentially undermine the inferences drawn about the relationship between the independent variable and the dependent variable. See also control variables, experiment.
• Consent. See implied consent, informed consent.
• Consent form. Written agreement, signed by both parties in which the participant agrees to take part in the research and gives her or his permission for data to be used in specified ways.
• Constant comparison. Process of constantly comparing data to analytical categories and vice versa, as well comparing data with other data and each category with other categories, to develop higher level categories and further your analysis towards the emergence of a grounded theory. See also inductive approach; Grounded Theory Method.
• Construct validity. Extent to which your measurement questions actually measure the presence of those constructs you intended them to measure. See also convergent validity, discriminant validity.
• Consultancy report. See management report.
• Content Analysis. An analytical technique that codes and categorises qualitative data in order to analyse them quantitatively. content validity see face validity.
• Contextual data. Additional data recorded when collecting primary or secondary data that reveals background information about the setting and the data collection process.
• Contingency table. Technique for summarising data from two or more variables so that specific values can be read.
• Continuing access. Gaining agreed research access to an organisation on an incremental basis.
• Continuous data. Data whose values can theoretically take any value (sometimes within a restricted range) provided they can be measured with sufficient accuracy.
• Contrived data. Data that result from a researcher organising an experiment, interview or survey. See also natural data.
• Control group. Group in an experiment that, for the sake of comparison, does not receive the intervention in which you are interested. See also experiment, experimental group.
• Control variables. Unwanted but measurable variables that need to be kept constant to avoid them influencing the effect of the independent variable on the dependent variable. See also confounding variables, experiment.
• Controlled index language. The terms and phrases used by databases to index items within the database. If search terms do not match the controlled index language, the search is likely to be unsuccessful.
• Convenience sampling. Non-probability haphazard sampling procedure in which cases are selected only on the basis that they are easiest to obtain. See also haphazard sampling, non-probability sampling.
• Convergent validity. The overlap (or correlation) between two different scales that have been used to measure the same construct.
• Correlation. The extent to which two variables are related to each other. See also correlation coefficient, negative correlation, positive correlation.
• Correlation coefficient. Number between -1 and +1 representing the strength of the relationship between two ranked or numerical variables. A value of +1 represents a perfect positive correlation. A value of -1 represents a perfect negative correlation. Correlation coefficients between +1 and -1 represent weaker positive and negative correlations, a value of 0 meaning the variables are perfectly independent. See also negative correlation, Pearson's product moment correlation coefficient, positive
• Correlation,. Spearman's rank correlation coefficient.
• Coverage. The extent to which a data set covers the population it is intended to cover.
• Covering letter. Letter accompanying a questionnaire, which explains the purpose of the survey. See also introductory letter.
• Covert research. Research undertaken where those being researched are not aware of this fact.
• Cramer's V. Statistical test to measure the association between two variables within a table on a scale where 0 represents no association and 1 represents perfect association. Because the value of Cramer's V is always between 0 and 1, the relative strengths of significant associations between different pairs of variables can be compared.
• Creative thinking technique. One of a number of techniques for generating and refining research ideas based on non-rational criteria. These may be, for example, biased heavily in favour of the individual's preferences or the spontaneous ideas of the individual or others. See also brainstorming, Delphi technique, relevance tree.
• Criterion-related validity. Ability of a statistical test to make accurate predictions.
• Critical case sampling. A purposive sampling method which focuses on selecting those cases on the basis of making a point dramatically or because they are important. See also purposive sampling.
• Critical Discourse Analysis. Discourse Analysis that adopts a critical realist philosophy. See also Discourse Analysis.
• Critical ethnography. Ethnographic strategy that questions the status quo and often adopts an advocacy role to bring about change. See also ethnography, interpretive ethnography, realist ethnography.
• Critical incidence technique. A technique in which respondents are asked to describe in detail a critical incident or number of incidents that is key to the research question. See also critical incident.
• Critical incident. An activity or event where the consequences were so clear that the respondent has a definite idea regarding its effects.
• Critical review (literature review). Detailed and justified analysis and commentary of the merits and faults of the literature within a chosen area, which demonstrates familiarity with what is already known about your research topic.
• Critical realism. The philosophical stance that what we experience are some of the manifestations of the things in the real world, rather than the actual things. See also direct realism, realism.
• Cronbach's alpha. Statistic used to measure the consistency of responses across a set of questions (scale items) designed together to measure a particular concept (scale). It consists of an alpha coefficient with a value between 0 and 1. Values of 0.7 or above suggest that the questions in the scale are measuring the same thing. See also scale item, scale.
• Cross-posting. Receipt by individuals of multiple copies of an email, often due to the use of multiple mailing lists on which that individual appears.
• Cross-sectional research. The study of a particular phenomenon (or phenomena) at a particular time, i.e. a 'snapshot'.
• Cross-tabulation. See contingency table.
• Data. Facts, opinions and statistics that have been collected together and recorded for reference or for analysis.
• Data display and analysis. A process for the collection and analysis of qualitative data that involves three concurrent subprocesses of data reduction, data display, and drawing and verifying conclusions.
• Data matrix. The table format in which data are usually entered into analysis software consisting of rows (cases) and columns (variables).
• Data reduction. Condensing data by summarising or simplifying these as a means to analyse them. See also data display and analysis.
• Data requirements table. A table designed to ensure that, when completed, the data collected will enable the research question(s) to be answered and the objectives achieved.
• Data sampling. The process of only transcribing those sections of an audio-recording that are pertinent to your research, having listened to it repeatedly beforehand.
• Data saturation. The stage when any additional data collected provides few, if any, new insights.
• Debriefing. Providing research participants with a retrospective explanation about a research project and its purpose where covert observation has occurred.
• Deception. Deceiving participants about the nature, purpose or use of research by the researcher(s). See also informed consent, research ethics.
• Decile. One of 10 sections when data are ranked and divided into 10 groups of equal size.
• Deductive approach. Approach to theory development involving the testing of a theoretical proposition by the employment of a research strategy specifically designed for the purpose of its testing.
• Deliberate distortion. Form of bias that occurs when data are recorded inaccurately on purpose. It is most common for secondary data sources such as organisational records.
• Delivery and collection questionnaire. Data collection technique in which the questionnaire is delivered to each respondent. She or he then reads and answers the same set of questions in a predetermined order without an interviewer being present before the completed questionnaire is collected.
• Delphi technique. Technique using a group of people who are either involved or interested in the research topic to generate and select a more specific research idea.
• Demographic variable. Variable that records data about characteristics.
• Deontological view. View that the ends served by research can never justify research which is unethical.
• Dependent variable. Variable that changes in response to changes in other variables.
• Descriptive data. Data whose values cannot be measured numerically but can be distinguished by classifying into sets (categories).
• Descriptive observation. Observation where the researcher concentrates on observing the physical setting, the key participants and their activities, particular events and their sequence and the attendant processes and emotions involved.
• Descriptive research. Research for which the purpose is to produce an accurate representation of persons, events or situations.
• Descriptive statistics. Generic term for statistics that can be used to describe variables.
• Descripto-explanatory study. A study whose purpose is both descriptive and explanatory where, usually, description is the precursor to explanation.
• Deviant sampling. See extreme case sampling.
• Dichotomous data. Descriptive data that are grouped into two categories. See also descriptive data.
• Direct realism. The philosophical stance that what you see is what you get: what we experience through our senses portrays the world accurately. See also critical realism, realism.
• Directional hypothesis. Testable statement of the direction of the association, difference or relationship between two or more variables. See also alternative hypothesis, hypothesis, null hypothesis.
• Directional null hypothesis. Testable statement that there is no directional association, difference or relationship between two or more variables. See also alternative hypothesis, directional hypothesis, null hypothesis.
• Discourse. Term used in discourse analysis to describe how language is used to shape meanings and give rise to social practices and relations. See also discourse analysis.
• Discourse analysis. General term covering a variety of approaches to the analysis of language in its own right. It explores how language constructs and simultaneously reproduces and/or changes the social world rather than using it as a means to reveal the social world as a phenomenon.
• Discrete data. Data whose values are measured in discrete units and therefore can take only one of a finite number of values from a scale that measures changes in this way.
• Discussion. The section of the project report in which the wider implications of the findings (and conclusions) are considered.
• Dispersion measures. Generic term for statistics that can be used to provide an impression of how the values for a variable are dispersed around the central tendency.
• Dissertation. The usual name for research projects undertaken as part of undergraduate and taught master's degrees. Dissertations are usually written for an academic audience.
• Divergent validity. The absence of overlap (or correlation) between different scales used to measure theoretically distinct constructs. See also construct validity.
• Document secondary data. Data that, unlike the spoken word endure physically (including digitally) as evidence allowing them to be transposed across both time and space and reanalysed for a purpose different to that for which they were originally collected.
• Document summary. Type of summary used an analytical aid. See also interim summary; transcript summary.
• DOI. Digital object identifier name used to uniquely identify an electronic document such as a specific journal article stored in an online database.
• Double-phase research design. Research involving two phases of data collection and analysis. See also sequential mixed methods research.
• Durbin–Watson statistic. Statistical test to measure the extent to which the value of a dependent variable at time t is related to its value at the previous time period, t - 1 (autocorrelation). The statistic ranges in value from zero to 4. A value of 2 indicates no autocorrelation. A value of towards zero indicates positive autocorrelation. A value towards 4 indicates negative autocorrelation. See also autocorrelation.
• Ecological validity. A type of external validity referring to the extent to which findings can be generalised from one group to another. See also external validity.
• Effect size index. A measure of the practical significance of a statistically significant difference, association or relationship. The statistic is normally used when the data sample is large.
• Electronic interview. An Internet- or intranet-mediated interview conducted through either a chat room, Internet forum, web conferencing or email. See also email interview, chat room, Internet forum.
• Electronic questionnaire. An Internet- or intranetmediated questionnaire. See also Internet-mediated questionnaire, intranet-mediated questionnaire.
• Element. Individual case or group member within a sample or population such as an employee.
• Email interview. A series of emails each containing a small number of questions rather than one email containing a series of questions.
• Embedded mixed-methods research. Use of quantitative and qualitative methods in research design where use of one is embedded within the other. See also concurrent embedded design, concurrent mixed methods research.
• Epistemological relativism. Subjectivist approach to knowledge that recognises knowledge is historically situated and that social facts are social constructions agreed on by people rather than existing independently.
• Epistemology. A branch of philosophy concerned with assumptions about knowledge, what constitutes acceptable, valid and legitimate knowledge, and how we can communicate knowledge to others.
• Ethics. See research ethics, research ethics committees, code of ethics.
• Ethnography. Research strategy that focuses upon describing and interpreting the social world throughfirsthand field study.
• Evaluation. The process of judging materials or methods in terms of internal accuracy and consistency or by comparison with external criteria.
• Event variable. Variable that records data about events, what happened in the past, now or will happen in the future.
• Existing contacts. Colleagues, friends, relatives or fellow students who may agree to become research informants, participants or respondents.
• Experiential data. Data about the researcher's perceptions and feelings as the research develops.
• Experiential meaning. The equivalence of meaning of a word or sentence for different people in their everyday experiences.
• Experiment. Research strategy whose purpose is to study the probability of a change in an independent variable causing a change in another, dependent variable. Involves the definition of null and alternative hypotheses; random allocation of participants to either an experimental group(s) or a control group; manipulation of the independent variable; measurement of changes in the dependent variable and; control of other variables. See also betweensubjects design, control group, experimental group, quasiexperiment.
• Experimental group. Group in an experiment that receives the intervention in which you are interested. See also control group, experiment.
• Explanation building. Deductive process for analysing qualitative data that involves the iterative examination of a number of strategically selected cases to test a theoretical proposition.
• Explanatory research. Research that focuses on studying a situation or a problem in order to explain the relationships between variables.
• Exploratory data analysis (EDA). Approach to data analysis that emphasises the use of diagrams to explore and understand the data.
• Exploratory study. Research that aims to seek new insights into phenomena, to ask questions, and to assess the phenomena in a new light.
• External researcher. Researcher who wishes to gain access to an organisation for which she or he does not work. See also access, internal researcher.
• External validity. The extent to which the research results from a particular study are generalisable to all relevant contexts.
• Extreme case sampling. A purposive sampling method which focuses on unusual or special cases. See also purposive sampling.
• Face validity. Agreement that a question, scale, or measure appears logically to reflect accurately what it was intended to measure.
• Factual variable. Variable that records factual data.
• [[Feasibility [of access]]]. Being able to negotiate access to conduct research.
• Filter question. Closed question that identifies those respondents for whom the following question or questions are not applicable, enabling them to skip these questions.
• Focus group. Group interview, composed of a small number of participants, facilitated by a 'moderator', in which the topic is defined clearly and precisely and there is a focus on enabling and recording interactive discussion between participants. See also group interview.
• Focused coding. Analysis or reanalysis of data to identify which of the initial codes may be used as higher level codes to categorise larger units of data to further the analysis towards the emergence of a grounded theory.
• Focused interview. Interviewer exercises direction over the interview while allowing the interviewee's opinions to emerge as he or she responds to the questions of the researcher.
• Focused observation. Phase in an observation study when the researcher focuses her or his observations on particular events or interactions between key informants.
• Follow-up. Contact made with respondents to thank them for completing and returning a survey and to remind nonrespondents to complete and return their surveys.
• Forced-choice question. See closed question.
• Forum see. Internet forum.
• Frequency distribution. Table for summarising data from one variable so that specific values can be read.
• Full-text online database. Online database that indexes and provides a summary and full text of articles from a range of journals. Sometimes includes books, chapters from books, reports, theses and conference papers.
• Fully integrated mixed-methods research. Use of both quantitative and qualitative methods throughout the research. See also partially integrated mixed methods research.
• Functionalist paradigm. Paradigm concerned with rational explanations and developing sets of recommendations within the current structures such as why a particular organisational problem is occurring in terms of the functions they perform.
• Fundamental research. See basic research.
• Gantt chart. Chart that provides a simple visual representation of the tasks or activities that make up a project, each being plotted against a time line.
• Gatekeeper. The person, often in an organisation, who controls research access.
• General focus research question. Question that flows from the research idea and may lead to several more detailed questions or the definition of research objectives.
• Generalisability. The extent to which the findings of a research study are applicable to other settings.
• Generalisation. The making of more widely applicable propositions based upon the process of deduction from specific cases.
• Goldilocks test. A test to decide whether research questions are either too big, too small, too hot or just right. Those that are too big probably demand too many resources. Questions that are too small are likely to be of insufficient substance, while those that are too hot may be so because of sensitivities that may be aroused as a result of doing the research.
• Grammatical error. Error of grammar that detracts from the authority of the project report.
• Graph. A visual display that illustrates the values of one variable or the relationship between two or more variables.
• Grey literature. See primary literature.
• Grounded theory. (1) Including both Grounded Theory Methodology and Grounded Theory Method. (2) Theory that is grounded or developed using an inductive approach. See also Grounded Theory Methodology, Grounded Theory Method, inductive approach.
• Grounded Theory (Methodology). Research strategy in which theory is developed from data collected by a series of observations or interviews principally involving an inductive approach. See also deductive approach, Grounded Theory Method, inductive approach.
• Grounded Theory Method. Data collection techniques and analytic procedures used in a Grounded Theory research strategy to derive meaning from the subjects and settings being studied. See also Grounded Theory (Methodology).
• Group interview. General term to describe all nonstandardised interviews conducted with two or more people.
• Habituation. Situation where, in observation studies, the subjects being observed become familiar with the process of observation so that they take it for granted. This is an attempt to overcome 'observer effect' or reactivity.
• Haphazard sampling. Non-probability sampling procedure in which cases are selected without any obvious principles of organisation. See also convenience sampling, nonprobability sampling.
• Hermeneutics. Strand of interpretivism that focuses on the study of cultural artefacts such as texts, symbols, stories, images. See also intepretivism.
• Heterogeneous sampling. A purposive sampling method which focuses on obtaining the maximum variation in the cases selected. See also purposive sampling.
• Heteroscedasticity. Extent to which the data values for the dependent and independent variables have unequal variances. See also variance.
• Histogram. Diagram for showing frequency distributions for a grouped continuous data variable in which the area of each bar represents the frequency of occurrence.
• Homogeneous sampling. A purposive sampling method which focuses on selecting cases from one particular subgroup in which all the members are similar. See also purposive sampling.
• Homoscedasticity. Extent to which the data values for the dependent and independent variables have equal variances. See also variance.
• Hybrid access. Use of both traditional access and Internetmediated access to conduct research.
• Hypothesis. (1) Testable statement that there is an association, difference or relationship between two or more variables. Often referred to as H1. See also alternative hypothesis, directional hypothesis, null hypothesis. (2) Testable proposition about the relationship between two or more events or concepts.
• Idiomatic meaning. The meaning ascribed to a group of words that are natural to a native speaker, but which is not deducible from the individual words.
• Incommensurability. The assertion that the radical humanist, radical structuralist, interpretive and functionalist paradigms contain mutually incompatible assumptions and therefore cannot be combined. See also functionalist paradigm, interpretive paradigm, radical humanist paradigm, radical structuralist paradigm.
• Independent groups t-test. Statistical test to determine the probability (likelihood) that the values of a numerical data variable for two independent samples or groups are different. The test assesses the likelihood of any difference between these two groups occurring by chance alone.
• Independent measures. Use of more than one experimental group in an experiment where more than one intervention or manipulation is to be tested and measured.
• Independent variable. Variable that causes changes to a dependent variable or variables.
• In-depth interview. See unstructured interview.
• Index number. Summary data value calculated from a base period for numerical variables, to facilitate comparisons of trends or changes over time. See also base period.
• Inductive approach. Approach to theory development involving the development of a theory as a result of the observation of empirical data.
• Ineligible respondent. Respondent selected for a sample who does not meet the requirements of the research.
• Inference, statistical. See statistical inference.
• Inferred consent. Informants, participants or respondents may or may not fully understand the implications of taking part but their consent to participate, is inferred from their participating in the research. The researcher assumes that data may be recorded, analysed, used, stored or reported as she or he wishes without clarifying such issues with those who take part. See also informed consent.
• Informant error. Errors that occur when informants are observed in situations that are inconsistent with their normal behaviour patterns, leading to atypical responses. See also informants.
• Informant interview. Interview guided by the perceptions of the interviewee.
• Informant verification. Form of triangulation in which the researcher presents written accounts of, for example, interview notes to informants for them to verify the content. See also triangulation.
• Informants. Those who agree to be observed in participant observation or structured observation studies.
• Informed consent. Position achieved when intended participants are fully informed about the nature, purpose and use of research to be undertaken and their role within it, and where their consent to participate, if provided, is freely given. See also deception, implied consent.
• Initial coding. See open coding.
• Initial sample. Purposively selected initial case from which to collect and analyse data used in Grounded Theory. See also Grounded Theory Method.
• Instrument. See questionnaire.
• Integer. A whole number.
• Interdiscursivity. The way one discourse is introduced into another discourse within discourse analysis. See also discourse analysis.
• Inter-library loan. System for borrowing a book or obtaining a copy of a journal article from another library.
• Interim summary. Type of summary used to outline progress and to aid analysis. See also document summary; transcript summary.
• Internal researcher. Person who conducts research within an organisation for which they work. See also cognitive access, external researcher.
• Internal validity. Extent to which findings can be attributed to interventions rather than any flaws in your research design. See also measurement validity.
• Internet forum. Commonly referred to as web forums, message boards, discussion boards, discussion forums, discussion groups and bulletin boards. Usually only deal with one topic and discourage personal exchanges.
• Internet-mediated access. Use of Internet technologies to gain virtual access to conduct research.
• Internet-mediated observation. Adaptation of traditional observation from oral/visual/near to textual/digital/virtual to allow researchers purely to observe or participate with members of an online community to collect data.
• Internet questionnaire. Data collection technique in which the questionnaire is delivered online to each respondent. She or he then reads and answers the same set of questions in a predetermined order without an interviewer being present before returning it electronically. See also Web questionnaire, mobile questionnaire.
• Interpretive ethnography. Ethnographic strategy stressing subjectivity, reflection and identifying multiple meanings. See also ethnography, critical ethnography, realist ethnography.
• Interpretive paradigm. Paradigm concerned with he way humans attempt to make sense of the world around them; for example, understanding the fundamental meanings attached to organisational life.
• Interpretivism. Philosophical stance that advocates humans are different from physical phenomena because they create meanings. Argues that argues that human beings and their social worlds cannot be studied in the same way as physical phenomena due to the need to take account of complexity.
• Inter-quartile range. The difference between the upper and lower quartiles, representing the middle 50% of the data when the data values for a variable have been ranked.
• Inter-rater reliability. The extent which two coders agree when coding the same set of data.
• Intertextuality. The way a text or texts overtly or covertly borrow from and are informed by other texts within Discourse Analysis. See also Discourse Analysis.
• Interval data. Numerical data for which the difference or 'interval' between any two data values for a particular variable can be stated, but for which the relative difference can not be stated. See also numerical data.
• Interview schedule. See structured interview.
• Interviewee bias. Attempt by an interviewee to construct an account that hides some data or when she or he presents herself or himself in a socially desirable role or situation.
• Interviewer bias. Attempt by an interviewer to introduce bias during the conduct of an interview, or where the appearance or behaviour of the interviewer has the effect of introducing bias in the interviewee's responses.
• Interviewer-completed questionnaire. Data collection technique in which an interviewer reads the same set of questions to the respondent in a predetermined order and records his or her responses. See also structured interview, telephone questionnaire.
• Intranet-mediated access. Use of an intranet within an organisation to gain access to conduct research.
• Intra-rater reliability. Reliability of coding by a single coder over time.
• Introduction. The opening to the project report, which gives the reader a clear idea of the central issue of concern of the research, states the research question(s) and research objectives, and explains the research context and the structure of the project report.
• Introductory letter. Request for research access, addressed to an intended participant or organisational broker/gatekeeper, stating the purpose of the research, the nature of the help being sought, and the requirements of agreeing to participate. See also covering letter, gatekeeper.
• Intrusive research methods. Methods that involve direct access to participants, including qualitative interviewing, observation, longitudinal research based on these methods and phenomenologically based approaches to research. See also access, cognitive access.
• Investigative question. One of a number of questions that need to be answered in order to address satisfactorily each research question and meet each objective.
• 'In vivo' codes. Names or labels for codes based on actual terms used by those who take part in research.
• Journal. See professional journal, refereed academic journal.
• Judgemental sampling. See purposive sampling.
• Kendall's rank correlation coefficient. Statistical test that assesses the strength of the relationship between two ranked data variables, especially where the data for a variable contain tied ranks. For data collected from a sample, there is also a need to calculate the probability of the correlation coefficient having occurred by chance alone.
• Key word. Basic term selected from the controlled index language specified by the online database to describe the research question(s) and objectives to search the tertiary literature.
• Kolmogorov–Smirnov test. Statistical test to determine the probability (likelihood) that an observed set of values for each category of a variable differs from a specified distribution. Common uses are to discover whether a data variable's distribution differs significantly from a normal distribution, or an alternative distribution such as that of the population from which it was selected.
• Kurtosis. The pointedness or flatness of a distribution's shape compared with the normal distribution. If a distribution is pointier or peaked, it is leptokurtic and the kurtosis value is positive. If a distribution is flatter, it is platykurtic and the kurtosis value is negative. See also normal distribution.
• Latent content. Meanings in the data that are not manifest and so need to be interpreted or inferred. See also Content Analysis, manifest content.
• Law of large numbers. Samples of larger absolute size are more likely to be representative of the population from which they are drawn than smaller samples and, in particular, the mean (average) calculated for the sample is more likely to equal the mean for the population, providing the samples are not biased.
• Level of access. The nature and depth of access to participants required and achieved. See also cognitive access, continuing access, physical access.
• Lexical meaning. The precise meaning of an individual word.
• Likert-style rating question. Rating question that allows the respondent to indicate how strongly she or he agrees or disagrees with a statement.
• Linearity. Degree to which change in a dependent variable is related to change in one or more independent variables. See also dependent variable, independent variable.
• Line graph. Diagram for showing trends in longitudinal data for a variable.
• List question. Closed question, in which the respondent is offered a list of items and instructed to select those that are appropriate.
• Literal replication. Replication of findings across selected multiple case studies in a case study strategy. See also case study, theoretical replication.
• Literature review. See critical (literature) review.
• Logical reasoning. Process used in theory development to explain why relationships may exist based on what is already known.
• Longitudinal study. The study of a particular phenomenon (or phenomena) over an extended period of time.
• Long-term trend. The overall direction of movement of numerical data values for a single variable after variations have been smoothed out. See also moving average.
• Lower quartile. The value below which a quarter of the data values lie when the data values for a variable have been ranked.
• Mail questionnaire. See postal questionnaire.
• Management report. Abbreviated version of the project report, usually written for a practitioner audience. Normally includes a brief account of objectives, method, findings, conclusions and recommendations.
• Manifest content. Content that is apparent in the data. See also Content Analysis, latent content.
• Mann–Whitney U test. Statistical test to determine the probability (likelihood) that the values of a ordinal data variable for two independent samples or groups are different. The test assesses the likelihood of any difference between these two groups occurring by chance alone and is often used when the assumptions of the independent samples t-test are not met.
• Matched pair analysis. Used in an experimental design to match participants in an experimental group with those in a control group before conducting the experiment where random assignment is not possible. See also quasi-experiment.
• Matrix question. Series of two or more closed questions in which each respondent's answers are recorded using the same grid.
• Maximum variation sampling. See heterogeneous sampling.
• Mean. The average value calculated by adding up the values of each case for a variable and dividing by the total number of cases.
• Measurement validity. The extent to which a scale or measuring instrument measures what it is intended to measure. See also internal validity.
• Median. The middle value when all the values of a variable are arranged in rank order; sometimes known as the 50th percentile.
• Mediating variable. A variable that transmits the effect of an independent variable to a dependent variable. See also dependent variable, independent variable.
• Member validation. Process of allowing participants to comment on and correct data to validate these.
• Memo writing. Key element used in Grounded Theory Method during the collection, analysis and interpretation of data, which helps to facilitate and link these stages of research and aid the development of a grounded theory. May also be used in other research strategies.
• Method. The techniques and procedures used to obtain and analyse research data, including for example questionnaires, observation, interviews, and statistical and nonstatistical techniques.
• Methodology. The theory of how research should be undertaken, including the theoretical and philosophical assumptions upon which research is based and the implications of these for the method or methods adopted.
• Minimal interaction. Process in which the observer tries as much as possible to 'melt into the background', having as little interaction as possible with the subjects of the observation. This is an attempt to overcome observer effect. See also observer effect.
• Mixed methods research. Use of both quantitative and qualitative data collection techniques and analysis procedures either at the same time (concurrent) or one after the other (sequential).
• Mixed-model research. Combination of quantitative and qualitative data collection techniques and analysis procedures as well as combining quantitative and qualitative approaches in other phases of the research such as research question generation.
• Mobile questionnaire. Data collection technique in which the questionnaire is delivered electronically to each respondent's mobile telephone. She or he then reads and answers the same set of questions in a predetermined order without an interviewer being present before returning it electronically. See also online questionnaire.
• Modal group. The most frequently occurring category for data that have been grouped.
• Mode. The value of a variable that occurs most frequently.
• Mode 0 knowledge creation. Research based on power and patronage, these being particularly visible in the close relationships between sponsor and researcher.
• Mode 1 knowledge creation. Research of a fundamental rather than applied nature, in which the questions are set and solved by academic interests with little, if any, focus on exploitation of research by practitioners.
• Mode 2 knowledge creation. Research of an applied nature, governed by the world of practice and highlighting the importance of collaboration both with and between practitioners.
• Mode 3 knowledge creation. Research growing out of Mode 1 and Mode 2 whose purpose is 'to assure survival and promote the common good at various levels of social aggregation' (Huff and Huff 2001:S53).
• Moderating variable. A variable that affects the relationship between an independent variable and a dependent variable. See also dependent variable, independent variable.
• Moderator. Facilitator of focus group interviews. See also focus group, group interview.
• Mono method. Use of a single data collection technique and corresponding analysis procedure or procedures.
• Moving average. Statistical method of smoothing out variations in numerical data recorded for a single variable over time to enable the long-term trend to be seen more clearly. See also long-term trend.
• Multicollinearity. See collinearity.
• Multi-method. Use of more than one data collection technique and corresponding analysis procedure or procedures.
• Multi-method qualitative study. Use of more than one qualitative data collection technique and corresponding qualitative analysis procedure or procedures.
• Multi-method quantitative study. Use of more than one quantitative data collection technique and corresponding quantitative analysis procedure or procedures.
• Multi-phase research design. Research involving more than two phases of data collection and analysis. See also sequential mixed methods research.
• Multiple bar graph]]/[[chart. Diagram for comparing frequency distributions for categorical or grouped discrete or continuous data variables, which highlights the highest and lowest values.
• Multiple-dichotomy method. Method of data coding using a separate variable for each possible response to an open question or an item in a list question. See also list question, open question.
• Multiple line graph. Diagram for comparing trends over time between numerical data variables.
• Multiple methods. Use of more than one data collection technique and analysis procedure or procedures. See also mixed methods.
• Multiple regression analysis. The process of calculating a coefficient of multiple determination and regression equation using two or more independent variables and one dependent variable. For data collected from a sample, there is also a need to calculate the probability of the regression coefficient having occurred by chance alone. See also multiple regression coefficient, regression analysis, regression equation.
• Multiple-response method. Method of data coding using the same number of variables as the maximum number of responses to an open question or a list question by any one case. See also list question, open question.
• Multiple-source secondary data. Secondary data created by combining two or more different data sets prior to the data being accessed for the research. These data sets can be based entirely on documentary or on survey data, or can be an amalgam of the two.
• Multi-stage sampling. Probability sampling procedure that is a development of cluster sampling. It involves taking a series of cluster samples, each of which uses random sampling (systematic, stratified or simple).
• Narrative. A personal account that interprets an event or series of events, which is significant for the narrator and which convey meaning to the researcher, and which are narrated in a sequenced way. See also narrative inquiry.
• Narrative Analysis. The collection and analysis of qualitative data that preserves the integrity and narrative value of data collected, thereby avoiding their fragmentation.
• Narrative inquiry. Qualitative research strategy to collect the experiences of participants as whole accounts or narratives, or which attempts to reconstruct such experiences into narratives. See also narrative.
• Natural data. Data that are recorded from real conversations that take place in everyday, authentic situations. See also contrived data.
• Naturalistic. Adopting an ethnographic strategy in which the researcher researches the phenomenon within the context in which it occurs.
• Negative cases. Cases that do not support emergent explanations, but which help the refining of these explanations and direct the selection of further cases to collect data.
• Negative correlation. Relationship between two variables for which, as the values of one variable increase, the values of the other variable decrease. See also correlation coefficient.
• Negative skew. Distribution of numerical data for a variable in which the majority of the data are found bunched to the right, with a long tail to the left.
• Netiquette. General operating guidelines for using the Internet, including not sending junk emails.
• New contacts. People approached to become research informants, participants or respondents previously unknown to the researcher.
• Nominal data. See descriptive data.
• Nominalism. Ontological position that asserts that the order and structures of social phenomena (and the phenomena themselves) are created by social actors through use of language, conceptual categories, perceptions and consequent actions.
• Non-maleficence. Avoidance of harm.
• Non-parametric statistic. Statistic designed to be used when data are not normally distributed. Often used with categorical data. See also categorical data.
• Non-probability sampling. Selection of sampling techniques in which the chance or probability of each case being selected is not known.
• Non-random sampling. See non-probability sampling.
• Non-response. When the respondent refuses to take part in the research or answer a question.
• Non-response bias. Bias in findings caused by respondent refusing to take part in the research or answer a question.
• Non-standardised interview. See semi-structured interview, unstructured interview.
• Normal distribution. Special form of the symmetric distribution in which the numerical data for a variable can be plotted as a bell-shaped curve.
• Notebook of ideas. Books or equivalent for noting down any interesting research ideas as you think of them.
• Null hypothesis. Testable statement stating that there is no association, difference or relationship between two or more variables. Often referred to as H0. See also alternative hypothesis, directional null hypothesis, hypothesis.
• Numeric rating question. Rating question that uses numbers as response options to identify and record the respondent's response. The end response options, and sometimes the middle, are labelled.
• Numerical data. Data whose values can be measured numerically as quantities.
• Objectivism. An ontological position that incorporates the assumptions of the natural sciences arguing that social reality is external external to, and independent of, social actors concerned with their existence. See also ontology, subjectivism.
• Objectivity. Avoidance of (conscious) bias and subjective selection during the conduct and reporting of research. In some research philosophies the researcher will consider that interpretation is likely to be related to a set of values and therefore will attempt to recognise and explore this.
• Observation. The systematic observing, recording, description, analysis and interpretation of people's behaviour. See also participant observation, structured observation.
• Observer as participant. Observational role in which the researcher observes activities without taking part in those activities in the same way as the 'real' research subjects. The researcher's identity as a researcher and research purpose is clear to all concerned. See also participant as observer.
• Observer bias. This may occur when observers give inaccurate responses in order to distort the results of the research.
• Observer drift. Occurs when the observer starts to redefine the way in which similar observations are interpreted leading to inconsistency.
• Observer effect. The impact of being observed on how people act. See also habituation, reactivity.
• Observer error. Systematic errors made by observers, as a result of tiredness, for example.
• One stage cluster sampling. See cluster sampling.
• One-way analysis of variance. See analysis of variance.
• Online first. The publication of forthcoming articles online, prior to them appearing in a journal.
• Online form (questionnaire). See Internet questionnaire.
• Online questionnaire. See Internet questionnaire.
• Ontology. Branch of philosophy concerned with assumptions about the nature of reality or being. See also axiology, epistemology.
• Open coding. The process of disaggregating data into units in grounded theory.
• Open question. Question allowing respondents to give answers in their own way.
• Operationalisation. The translation of concepts into tangible indicators of their existence.
• Opinion variable. Variable that records what respondents believe about something, what they think is true or false.
• Ordinal data. See ranked data.
• Outlier. A case or unit of analysis that has extreme values for a variable which may distort the interpretation of data or make a statistic misleading.
• Paired t-test. Statistical test to determine the probability (likelihood) that the values of two (a pair of) numerical data variables collected for the same cases are different. The test assesses the likelihood of any difference between two variables (each half of the pair) occurring by chance alone.
• Paradigm. A set of basic and taken-for-granted assumptions which underwrite the frame of reference, mode of theorising and ways of working in which a group operates.
• Parametric statistic. Statistic designed to be used when data are normally distributed. Used with numerical data. See also numerical data.
• Partial response. The level of response to questionnaires or structured interviews in which 50% to 80% of all questions are answered other than by a refusal or no answer.
• Partially integrated mixed-methods research. Use of both quantitative and qualitative methods at only one stage or at particular stages of the research. See also fully integrated mixed methods research.
• Participant. The person who answers the questions, usually in an interview or group interview.
• Participant as observer. Observational role in which the researcher takes part in and observes activities in the same way as the 'real' research subjects. The researcher's identity as a researcher and research purpose is clear to all concerned. See also observer as participant.
• Participation bias. Type of bias resulting from the nature of the individuals or organisational participants who agree to take part in a research study.
• Participant information sheet. Document providing information required by gatekeepers and intended participants in order for informed consent to be given.
• Participant observation. Observation in which the researcher attempts to participate fully in the lives and activities of the research subjects and thus becomes a member of the subjects' group(s), organisation(s) or community. See also complete observer, complete participant, observer as participant, participant as observer.
• Participant researcher. See internal researcher.
• Participant validation. See member validation.
• Passive voice. The voice in which the subject of the sentence undergoes the action of the verb: for example, 'interviews were conducted'.
• Pattern matching. Analysis of qualitative data involving the prediction of a pattern of outcomes based on theoretical propositions to seek to explain a set of findings.
• Pearson's product moment correlation coefficient. Statistical test that assesses the strength of the relationship between two numerical data variables. For data collected from a sample there is also a need to calculate the probability of the correlation coefficient having occurred by chance alone.
• Percentage component bar graph/chart. Diagram for comparing proportions for all types of data variables.
• Percentile. One of 100 sections when data are ranked and divided into 100 groups of equal size.
• Personal data. Category of data, defined in law, relating to identified or identifiable persons. See also sensitive personal data.
• Personal entry. Situation where the researcher needs to conduct research within an organisation, rather than rely on the use and completion of self-administered, postal questionnaires or the use of publicly available secondary data. See access.
• Personal pronoun. One of the pronouns used to refer to people: I, me, you, he, she, we, us, they, him, her, them.
• Phenomenology. Strand of interpretivism that focuses on participants' lived experience, that is the participants' recollections and interpretations of those experiences, being particularly concerned with generating meanings and gaining insights into those phenomena. See also interpretivism.
• Phi. Statistic to measure association between two variables using a scale between -1 (perfect negative association), through 0 (no association) to +1 (perfect association).
• Physical access. The initial level of gaining access to an organisation to conduct research. See also cognitive access, continuing access, gatekeeper.
• Pictogram. Diagram in which a picture or series of pictures are used to represent the data proportionally.
• Pie chart. Diagram frequently used for showing proportions for a categorical data or a grouped continuous or discrete data variable.
• Pilot test. Small-scale study to test a questionnaire, interview checklist or observation schedule, to minimise the likelihood of respondents having problems in answering the questions and of data recording problems as well as to allow some assessment of the questions' validity and the reliability of the data that will be collected.
• Plagiarism. Presenting work or ideas as if they are your own when in reality they are the work or ideas of someone else, and failing to acknowledge the original source.
• Population. The complete set of cases or group members. See also research population.
• Positive correlation. Relationship between two variables for which, as the value of one variable increases, the values of the other variable also increase. See also correlation coefficient.
• Positive skew. Distribution of numerical data for a variable in which the majority of the data are found bunched to the left, with a long tail to the right.
• Positivism. The philosophical stance of the natural scientist entailing working with an observable social reality to
• Produce law-like generalisations. The emphasis is on highly structured methodology to facilitate replication.
• Postal questionnaire. Data collection technique in which the questionnaire is delivered by post to each respondent. She or he then reads and answers the same set of questions in a predetermined order without an interviewer being present before returning it by post.
• Postmodernism. Philosophical stance emphasising the role of language and power-relations that seeks to question accepted ways of thinking and give voice to alternative marginalised views.
• Post-test. Outcome measurement for the dependent variable in an experiment. See also pre-test.
• PowerPoint™. Microsoft computer package that allows the presenter to design overhead slides using text, pictures, photographs etc., which lend a professional appearance.
• Practitioner-researcher. Role occupied by a researcher when she or he is conducting research in an organisation, often her or his own, while fulfilling her or his normal working role.
• Pragmatism. Philosophical stance that argues that concepts are only relevant where they support action. It considers research starts with a problem, and aims to contribute practical solutions that inform future practice. Pragmatists research may vary considerably in terms of how objectivist or subjectivist it is. See also objectivist, subjectivist.
• Pre-coding. The process of incorporating coding schemes in questions prior to a questionnaire's administration.
• Predictive validity. See criterion-related validity.
• Preliminary inquiry. The process by which a research idea is refined in order to turn it into a research project. This may be simply a review of the relevant literature
• Preliminary search. This way of searching the literature may be a useful way of generating research ideas. It may be based, for example, on lecture notes or course textbooks.
• Pre-set codes. Codes established prior to data collection and often included as part of the data collection form.
• Pre-survey contact. Contact made with a respondent to advise them of a forthcoming survey in which she or he will be asked to take part.
• Pre-test. Baseline measurement for the dependent variable in an experiment. See also post-test.
• Primary data. Data collected specifically for the research project being undertaken.
• Primary literature. The first occurrence of a piece of work, including published sources such as government white papers and planning documents and unpublished manuscript sources such as letters, memos and committee minutes.
• Primary observation. Observation where the researcher notes what happened or what was said at the time. This is often done by keeping a research diary.
• Privacy. Primary ethical concern relating to the rights of individuals not to participate in research and to their treatment where they agree to participate. See also research ethics, informed consent.
• Probability sampling. Selection of sampling techniques in which the chance, or probability, of each case being selected from the population is known and is not zero.
• Probing questions. Questions used to explore further responses that are of significance to the research topic.
• Professional journal. Journal produced by a professional organisation for its members, often containing articles of a practical nature related to professional needs. Articles in professional journals are usually not refereed.
• Project report. The term used in this book to refer generally to dissertations, theses and management reports. See also dissertation, management report, thesis.
• Pure research. See basic research.
• Purposive sampling. Non-probability sampling procedure in which the judgement of the researcher is used to select the cases that make up the sample. This can be done on the basis of extreme cases, heterogeneity (maximum variation), homogeneity (maximum similarity), critical cases, theoretical cases or typical cases.
• Qualitative data. Non-numerical data or data that have not been quantified.
• Qualitative interview. Collective term for semi-structured and unstructured interviews aimed at generating qualitative data.
• Qualitise. Conversion of quantitative data into narrative that can be analysed qualitatively.
• Quantifiable data. See numerical data.
• Quantitative data. Numerical data or data that have been quantified.
• Quantitise. Conversion of qualitative data into numerical codes that can be analysed statistically.
• Quantity question. Closed question in which the respondent's answer is recorded as a number giving the amount.
• Quartile. One of four sections when data are ranked and divided into four groups of equal size. See also lower quartile, upper quartile.
• Quasi-experiment. Experimental design using an experimental group and a control group but where experimental participants cannot be assigned randomly to each group. See also matched pair analysis.
• Questionnaire. General term including all data collection techniques in which each person is asked to respond to the same set of questions in a predetermined order. See also delivery and collection questionnaire, intervieweradministered questionnaire, online questionnaire, postal questionnaire, self-administered questionnaire.
• Quota sampling. Non-probability sampling procedure that ensures that the sample represents certain characteristics of the population chosen by the researcher.
• R2 value. See coefficient of determination.
• R2 value. See coefficient of multiple determination.
• Radical change perspective. A perspective which fundamentally question the way things are done in organisations, and, through research, offers insights that would help to change the organisational and social worlds.
• Radical humanist paradigm. Paradigm concerned with changing the status quo, focusing on issues of power and politics, domination and oppression and emphasising the importance of social construction, language, processes, and instability of structures and meanings.
• Radical structuralist paradigm. Paradigm concerned with achieving fundamental change based upon an analysis of phenomena such as structural power relationships and patterns of conflict.
• Random sampling. See simple random sampling.
• Range. The difference between the highest and the lowest values for a variable.
• Ranked data. Data whose values cannot be measured numerically but which can be placed in a definite order (rank).
• Ranking question. Closed question in which the respondent is offered a list of items and instructed to place them in rank order.
• Rating question. Closed question in which a scaling device is used to record the respondent's response. See also Likert-type rating question, numeric rating question, semantic differential rating question.
• Ratio data. Numerical data for which both the difference or 'interval' and relative difference between any two data values for a particular variable can be stated. See also numerical data.
• Rational thinking technique. One of a number of techniques for generating and refining research ideas based on a systematic approach such as searching the literature or examining past projects.
• Raw data. Data for which little, if any, data processing has taken place.
• Reactivity. Reaction by research participants to any research intervention that affects data reliability. See also habituation, observer effect.
• Realism. The epistemological position that objects exist independently of our knowledge of their existence. See also critical realism, direct realism.
• Realist ethnography. Ethnographic strategy stressing objectivity, factual reporting and identifying 'true' meanings. See also ethnography, critical ethnography, interpretive ethnography.
• Re-coding. The process of grouping or combining a variable's codes to form a new variable, usually with less detailed categories.
• Reductionism. The idea that problems as a whole are better understood if they are reduced to the simplest possible elements.
• Refereed academic journal. Journal in which the articles have been evaluated by academic peers prior to publication to assess their quality and suitability. Not all academic journals are refereed.
• References, list of. Bibliographic details of all items referred to directly in the text. The university will specify the format required.
• Reflection. Process of observing your own research practice and examining the way you do things.
• Reflective diary. Diary in which the researcher notes down what has happened and lessons learnt during the research process. See also research notebook.
• Reflexivity. Self-examination, evaluation and interpretation of your attitudes and beliefs, reactions to data and findings, and interactions with those who take part in the research and acknowledgement of the way these affect both the processes and outcomes of the research.
• Regression analysis. The process of calculating a regression coefficient and regression equation using one independent variable and one dependent variable. For data collected from a sample, there is also a need to calculate the probability of the regression coefficient having occurred by chance alone. See also multiple regression analysis, coefficient of determination, r 2 value, regression equation.
• Regression equation. Equation used to predict the values of a dependent variable given the values of one or more independent variables. The associated coefficient of determination provides an indication of how good a predictor the regression equation is likely to be. See coefficient of determination.
• Regulation perspective. A perspective concerned primarily with the need for the regulation of societies and human behavior. It seeks to explain the way in which organisational affairs are regulated and offer suggestions as to how they may be improved within the framework of the way things are done at present.
• Relevance tree. Technique for generating research topics that starts with a broad concept from which further (usually more specific) topics are generated. Each of these topics forms a separate branch, from which further sub-branches that are more detailed can be generated.
• Reliability. The extent to which data collection technique or techniques will yield consistent findings, similar observations would be made or conclusions reached by other researchers or there is transparency in how sense was made from the raw data.
• Repeated measures. See within-subjects design.
• Representative sample. Sample that represents exactly the population from which it is drawn.
• Representative sampling. See probability sampling.
• Research. The systematic collection and interpretation of information with a clear purpose, to find things out. See also applied research, basic research.
• Research approach. General term for inductive, deductive or abductive research approach. See also abductive approach, deductive approach, inductive approach.
• Research design. Framework for the collection and analysis of data to answer research question and meet research objectives providing reasoned justification for choice of data sources, collection methods and analysis techniques.
• Research ethics. The standards of the researcher's behaviour in relation to the rights of those who become the subject of a research project, or who are affected by it. See also code of ethics, privacy, research ethics committee.
• Research ethics committee. Learned committee established to produce a code of research ethics, examine and approve or veto research proposals and advise in relation to the ethical dilemmas facing researchers during the conduct and reporting of research projects. See also code of ethics.
• Research idea. Initial idea that may be worked up into a research project.
• Research interview. Purposeful conversation between two or more people requiring the interviewer to establish rapport, to ask concise and unambiguous questions and to listen attentively.
• Research notebook. Notebook in which the researcher records chronologically aspects of their research project such as useful articles they have read, notes of discussions with their project supervisor etc. and their emergent thoughts about all aspects of their research. Can be used as an analytical aid. Can incorporate a reflective diary. See also reflective diary; self-memo.
• Research objectives. Clear, specific statements that identify what the researcher wishes to accomplish as a result of doing the research.
• Research philosophy. Overarching term relating to a system of beliefs and assumptions about the development of knowledge and the nature of that knowledge in relation to research.
• Research proposal. Structured plan of a research project, occasionally referred to as a protocol or outline.
• Research question. The key question that the research process will address, or one of the key questions that it will address. The research question is generally the precursor of research objectives.
• Research strategy. General plan of how the researcher will go about answering the research question(s).
• Respondent. The person who answers the questions usually on a questionnaire. See also participant.
• Response bias. See interviewee bias.
• Response rate. The total number of responses divided by the total number in the sample after ineligible respondents have been excluded. See ineligible respondent. See also active response rate, break off, complete refusal, complete response, partial response.
• Review article. Article, normally published in a refereed academic journal, that contains both a considered review of the state of knowledge in a given topic area and pointers towards areas where further research needs to be undertaken. See also refereed academic journal.
• Review question. Specific question you ask of the material you are reading, which is linked either directly or indirectly to your research question. See also research question.
• Sample. Subgroup or part of a larger population.
• Sampling fraction. The proportion of the total population selected for a probability sample.
• Sampling frame. The complete list of all the cases in the population, from which a probability sample is drawn. saturation see data saturation.
• Scale. Measure of a concept, such as customer loyalty or organisational commitment, created by combining scores to a number of rating questions.
• Scale item. Rating question used in combination with other rating questions to create a scale. See rating question, scale.
• Scale question. See rating question.
• Scatter graph. Diagram for showing the relationship between two numerical or ranked data variables.
• Scatter plot. See scatter graph.
• Scientific research. Research that involves the systematic observation of and experiment with phenomena.
• Scoping study. Preliminary exploratory study undertaken as part of Systematic Review to establish whether Systematic Reviews have already been published and determine the focus of the literature search. See also Systematic Review.
• Search engine. Automated software that searches an index of documents on the Internet using key words and Boolean logic.
• Search string. Combination of key words or search terms used in searching online databases.
• Search term. Basic terms that describes your research question(s) and objectives, and is be used to search the tertiary literature.
• Secondary data. Data that were originally collected for some other purpose. They can be can be further analysed to provide additional or different knowledge, interpretations or conclusions. See also document secondary data, multiple source secondary data, survey-based secondary data.
• Secondary literature. Subsequent publication of primary literature such as books and journals.
• Secondary observation. Statement made by an observer of what happened or was said. By necessity this involves that observer's interpretations.
• Selective coding. The process of integrating categories to produce theory in grounded theory.
• Self-coded question. Question each respondent codes her or himself as part of the process of recording their answer.
• Self-completed questionnaire. Data collection technique in which each respondent reads and answers the same set of questions in a predetermined order without an interviewer being present.
• Self-memo. Way of recording own ideas about research as they occur, which may then be used as an analytical aid. See also research notebook.
• Self-selection sampling. Non-probability sampling procedure in which the case, usually an individual, is allowed to identify their desire to be part of the sample.
• Semantic differential rating question. Rating question that allows the respondent to indicate his or her attitude to a concept defined by opposite adjectives or phrases.
• Semi-structured interview. Wide-ranging category of interview in which the interviewer commences with a set of interview themes but is prepared to vary the order in which questions are asked and to ask new questions in the context of the research situation.
• Sensitive personal data. Category of data, defined in law, that refers to certain specified characteristics or beliefs relating to identified or identifiable persons.
• Sensitivity. Level of concern on the part of a potential host organisation, informant, participant or respondent about the nature of a research project and use of data that will affect willingness to cooperate.
• Sequential explanatory design. Mixed methods research design where initial phase of quantitative data collection is followed by second phase of explanatory qualitative data collection. See also sequential mixed methods research.
• Sequential exploratory design. Mixed methods research design where initial phase of exploratory qualitative data collection is followed by second phase of quantitative data collection. See also sequential mixed methods research.
• Sequential mixed-methods research. Research using both quantitative and qualitative methods that are conducted in more than one phase of data collection and analysis. See also double-phase research design, multiphase research design, sequential explanatory design, sequential exploratory design.
• Sequential multi-phase design. Mixed methods research design involving multiple phases of data collection and analysis.
• Serial correlation. See autocorrelation.
• Shadowing. Process that the researcher would follow in order to gain a better understanding of the research context. This might involve following employees who are likely to be important in the research.
• Shapiro–Wilk test. Statistical test to determine the probability (likelihood) that an observed set of values for each category of a variable differs from a specified distribution.
• Signficance testing. Testing the probability of a pattern such as a relationship between two variables occurring by chance alone if the null hypothesis were true.
• Simple random sampling. Probability sampling procedure that ensures each case in the population has an equal chance of being included in the sample.
• Single-phase research design. Research involving one phase of data collection and analysis. See also concurrent mixed methods research. See also concurrent mixed methods research.
• Snowball sampling. Non-probability sampling procedure in which subsequent respondents are obtained from information provided by initial respondents.
• Social constructionism. Ontological position that asserts that reality is constructed through social interaction in which social actors create partially shared meanings and realities, in other words it is socially constructed.
• Social norm. The type of behaviour that a person ought to adopt in a particular situation.
• Socially desirable response. Answer given by a respondent due to her or his desire, either conscious or unconscious, to gain prestige or appear in a different social role.
• Source questionnaire. The questionnaire that is to be translated from another language when translating a questionnaire.
• Spearman's rank correlation coefficient. Statistical test that assesses the strength of the relationship between two ranked data variables. For data collected from a sample, there is also a need to calculate the probability of the correlation coefficient having occurred by chance alone.
• Split infinitive. Phrase consisting of an infinitive with an adverb inserted between 'to' and the verb: for example, 'to readily agree'.
• Stacked bar graph/chart. Diagram for comparing totals and subtotals for all types of data variable.
• Standard deviation. Statistic that describes the extent of spread of data values around the mean for a variable containing numerical data.
• Statistical inference. The process of coming to conclusions about the population on the basis of data describing a sample drawn from that population.
• Statistical significance. The likelihood of the pattern that is observed (or one more extreme) occurring by chance alone, if there really was no difference in the population from that which the sample was drawn.
• Storyline. The way in which the reader is led through the research project to the main conclusion or the answer to the research question. The storyline is, in effect, a clear theme that runs through the whole of the project report to convey a coherent and consistent message.
• Stratified random sampling. Probability sampling procedure in which the population is divided into two or more relevant strata and a random sample (systematic or simple) is drawn from each of the strata.
• Structural narrative analysis. Narrative Analysis that focuses on the way a narrative is constructed. See also Narrative Analysis.
• Structured interview. Data collection technique in which an interviewer physically meets the respondent, reads them the same set of questions in a predetermined order, and records his or her response to each.
• Structured methodology. Data collection methods that are easily replicated (such as the use of an observation schedule or questionnaire) to ensure high reliability.
• Structured observation. Observation method using a high level of predetermined structure, often used to quantify observed behaviours. See also participant observation.
• Subject directory. Hierarchically organised index categorised into broad topics, which, as it has been compiled by people, is likely to have its content partly censored and evaluated.
• Subject bias or participant bias. Bias that may occur when research subjects are giving inaccurate responses in order to distort the results of the research.
• Subjectivism. Ontological position that incorporates assumptions of the Arts and Humanities and asserts that social reality is made from the perceptions and consequent actions of social actors (people). See also ontology, objectivism.
• [[Sufficiency [of access]]]. Being able to negotiate adequate access to conduct research.
• Survey. Research strategy that involves the structured collection of data from a sizeable population. Although the term 'survey' is often used to describe the collection of data using questionnaires, it includes other techniques such as structured observation and structured interviews.
• Survey-based secondary data. Data collected by surveys, such as by questionnaire, which have already been analysed for their original purpose.
• Symbolic interactionism. Strand of interpretivism derived from pragmatist thinking that sees meaning as something that emerges out of interactions between people. It focuses on the observation and analysis of social interaction such as conversations, meetings and teamwork. See also interpretivism, pragmatism.
• Symmetric distribution. Description of the distribution of data for a variable in which the data are distributed equally either side of the highest frequency.
• Symmetry of potential outcomes. Situation in which the results of the research will be of similar value whatever they are.
• Synchronous. Undertaken in real time, occurring at the same time.
• Synthesis. Process of arranging and assembling various elements so as to make a new statement, or conclusion.
• Systematic random sampling. Probability sampling procedure in which the initial sampling point is selected at random, and then the cases are selected at regular intervals.
• Systematic Review. A process for reviewing the literature using a comprehensive pre-planned strategy to locate existing literature, evaluate the contribution, analyse and synthesise the findings and report the evidence to allow conclusions to be reached about what is known and, also, what is not known.
• Systematic sampling. See systematic random sampling.
• Table. Technique for summarising data from one or more variables so that specific values can be read. See also contingency table, frequency distribution.
• Tailored design method. Approach to designing questionnaires specifying precisely how to construct and use them; previously referred to as the 'total design method'.
• Target population. Complete set of cases or group members that is the actual focus of the research inquiry, and from which a sample may be drawn.
• Target questionnaire. The translated questionnaire when translating from a source questionnaire.
• Teleological view. View that the ends served by research justify the means. Consequently, the benefits of research findings are weighed against the costs of acting unethically.
• Telephone questionnaire. Data collection technique in which an interviewer contacts the respondent and administers the questionnaire using a telephone. The interviewer reads the same set of questions to the respondent in a predetermined order and records his or her responses.
• Template Analysis. Analysis of qualitative data that involves creating and developing a hierarchical template of data codes or categories representing themes revealed in the data collected and the relationships between these.
• Tense. The form taken by the verb to indicate the time of the action (i.e. past, present or future).
• Tertiary literature source. Source designed to help locate primary and secondary literature, such as an index, abstract, encyclopaedia or bibliography.
• Thematic Analysis. A technique used to analyse qualitative data that involves the search for themes, or patterns, occurring across a data set.
• Thematic narrative analysis. Narrative Analysis that focuses on the thematic content of a narrative, rather than on the way in which it is structured. See also Narrative Analysis.
• Theme. A broad category incorporating several codes that appear to be related to one another and which indicates an idea that is important to your research question.
• Theoretical replication. Realisation or replication of predicted theoretical outcomes in selected case studies in a case study strategy. See also case study, literal replication.
• Theoretical sampling. A purposive sampling method particularly associated with Grounded Theory which focuses on the needs of the emerging theory and the evolving story line, participants being chosen purposively to inform this.
• Theoretical saturation. Procedure used in Grounded Theory Method and reached when data collection ceases to reveal new data that are relevant to a category, where categories have become well developed and understood and relationships between categories have been verified. See also Grounded Theory Method.
• Theoretical sensitivity. Sensitivity to meanings in the data and using in vivo and researcher generated codes to guide theorising activity, rather than being sensitised by concepts in existing theory.
• Theory. Formulation regarding the cause and effect relationships between two or more variables, which may or may not have been tested.
• Thesis. The usual name for research project reports undertaken for Master of Philosophy (MPhil) and Doctor of Philosophy (PhD) degrees, written for an academic audience.
• Time error. Error, usually associated with structured observations, where the time at which the observation is being conducted provides data that are untypical of the time period in which the event(s) being studied would normally occur.
• Time series. Set of numerical data values recorded for a single variable over time usually at regular intervals. See also moving average.
• Total response rate. The total number of responses divided by the total number in the sample after ineligible respondents have been excluded. See ineligible respondent. See also active response rate, break off, complete response, complete refusal, partial response.
• Trade journal. Journal produced by a trade organisation for its members, often containing articles of a practical nature related to the trade's needs. Articles in trade journals are usually not refereed.
• Traditional access. Use of face-to-face interactions, correspondence for postal questionnaires, 'phone conversations or visits to data archives to conduct research.
• Transcript. The written record of what a participant (or respondent) said in response to a question, or what participants (or respondents) said to one another in conversation, in their own words.
• Transcript summary. Type of summary produced following the transcription of an interview or observation and used as an analytical aid. See also document summary; interim summary.
• Triangulation. The use of two or more independent sources of data or data-collection methods within one study in order to help ensure that the data are telling you what you think they are telling you.
• Trimmed mean. A mean calculated after extreme values (known as outliers) have been excluded.
• T-test. See independent groups t-test, paired t-test.
• Type I error. Error made by wrongly coming to the decision that something is true when in reality it is not.
• Type II error. Error made by wrongly coming to the decision that something is not true when in reality it is.
• Type of access. Way used to gaining access to conduct research. See also Internet-mediated access, intranetmediated access, hybrid access, traditional access.
• Typical case sampling. A purposive sampling method which focuses on selecting cases on the basis that they are typical or illustrative. See also purposive sampling.
• Uninformed response. Tendency for a respondent to deliberately guess where they have sufficient knowledge or experience to answer a question.
• Unitising data. The process of attaching relevant 'bits' or 'chunks' of your data to the appropriate category or categories that you have devised.
• Unit of data. A number of words, a line of a transcript, a sentence, a number of sentences, a complete paragraph, or some other single chunk of textual data or visual image that will be coded. See also code, coding.
• Unreachable respondent. Respondent selected for a sample who cannot be located or who cannot be contacted.
• Unstructured interview. Loosely structured and informally conducted interview that may commence with one or more themes to explore with participants but without a predetermined list of questions to work through. See also informant interview.
• Upper quartile. The value above which a quarter of the data values lie when the data values for a variable have been ranked.
• URL. Uniform resource locator specifying where a known resource can be found.
• Validity. (1) The extent to which data collection method or methods accurately measure what they were intended to measure. (2) The extent to which research findings are really about what they profess to be about. See also construct validity, criterion related validity, ecological validity, face validity, internal validity, measurement validity, predictive validity.
• Variable. Individual element or attribute upon which data have been collected.
• Variance. Statistic that measures the spread of data values; a measure of dispersion. The smaller the variance, the closer individual data values are to the mean. The value of the variance is the square of the standard deviation. See also dispersion measures, standard deviation.
• Variance inflation factor (VIF). Statistic used to measure collinearity see collinearity.
• Videography. (1) the process of recording moving images onto electronic media; (2) the ethnographic analysis of recorded video sequences.
• VIF. See variance inflation factor.
• Virtual access. The initial level of gaining access to online communities to conduct research. See also cognitive access, continuing access, gatekeeper.
• Visual aid. Item such as an overhead projector slide, whiteboard, video recording or handout that is designed to enhance professional presentation and the learning of the audience.
• Web log. See blog.
• Web questionnaire. Data collection technique in which the questionnaire is delivered electronically to each respondent's email address. She or he then reads and answers the same set of questions in a predetermined order without an interviewer being present before returning it electronically. See also online questionnaire.
• Weighting. The process by which data values are adjusted to reflect differences in the proportion of the population that each case represents.
• Within-subjects design. Experimental design using only a single group where every participant is exposed to the planned intervention or series of interventions. See also experiment, between-subjects design.