ANALYSIS: A process of working with the data to describe, discuss, interpret, evaluate and explain the data in terms of the research questions or hypothesis of the research project.
ASSOCIATION OR ASSOCIATIVE RELATIONSHIP: the belief that there is a relationship between two concepts, but not necessarily that the relationship is causal.
ASYNCHRONOUS COMMUNICATION: Communication between people where all the communicants are not, necessarily, in contact at the same moment in time.
ATHEORETICAL: Refers to the absence of an underpinning theory or set of ideas.
AXIAL CODING: In Grounded Theory data analysis, this is the second stage of coding data, and involves relating codes to each other.
BIAS: Prejudice in favour, or against, a group individual, perspective, etc.
BIVARIATE ANALYSIS: The analysis of two variables together.
CASE STUDY: The study of a single entity, often a person, an organisation, a situation or a country, wherein the subject is explored in detail and great depth.
CAUSAL RELATIONSHIP: The assertion that a change in ‘A’ causes a change in ‘B’.
CENTRAL TENDENCY: A statistical measure which summarises the data relating to one variable in one value, such as the mean, median or mode.
CHAT ROOMS: Online discussion forums allowing synchronous or asynchronous communication.
CHECK BOXES: On an electronic questionnaire, boxes that can be ticked by respondents in response to a question.
CHI-SQUARED: A test that can be used to assess whether the difference between the mean values of two samples is statistically significant.
CLUSTER SAMPLE: A sample consisting of cases selected because of their proximity to one another.
CODE: A way of identifying a specific answer or characteristic. It may be numeric or alphabetic.
CODING: The process of ‘marking’ or identifying data for later analysis.
COHORT STUDIES: A type of longitudinal study which looks at a group of people of the same age and then gathers data about them at set points throughout their lives.
COMPARATIVE RESEARCH: A research strategy used to study two or more subjects, often countries or cultures.
COMPUTER-MEDIATED COMMUNICATION (CMC): The use of computers and the internet for communication between people.
CONCEPT: An idea, abstraction or construct that encapsulates a way of describing, thinking about or labelling a social phenomenon. Some commonly used concepts in social research are ethnicity, health, family, employment, social class and lifestyle.
CONSTANT COMPARISON: Comparing data from different sources and from different places and times to support the analysis, along with the search for negative cases.
CONSTRUCTIVISM: An ontological position which asserts that the social phenomena making up our social world are only real in the sense that they are constructed ideas which are continually being reviewed and reworked by those involved in them through social interaction and reflection.
CONTENT ANALYSIS: A technique for examining the categories that the data comprise and condensing them into fewer numbers so that they are easier to understand.
CONTROL GROUP: In a research design, this is a group of people or materials that are the same as the experimental group in every way except the aspect of manipulation or change.
CORRELATION COEFFICIENT: A statistic that provides a measure of the strength and direction of a relationship between two ratio variables.
COVERT METHODS: Methods of investigation in which participants are not aware that they are part of a research project, or are perhaps being observed in secret.
CREDIBILITY: The credibility (or believability) of the researcher’s interpretations of the data she has gathered is tested by the analysis and interpretation of data being transparent, for example, by testing out the interpretation of the data with the research participants or by setting the interpretations alongside existing theory.
CRITICAL APPROACH: The way in which we use judgement (and other things such as experience or observation) to evaluate data, information, knowledge, etc. When we say ‘critical’ we do not mean it in a negative sense, we mean ‘evaluate’.
CRITICAL REALISM: A position that prioritises identifying structures or mechanisms that result in inequality or injustice and thus offers the opportunity for social change by changing or negating the structural mechanisms that are identified as having these impacts.
CRITICAL REALIST APPROACH: This usually means: collecting qualitative and/or quantitative data; revealing hidden structures and mechanisms; uncovering power relations and dominant ideologies; research that leads to action.
CROSS-SECTIONAL RESEARCH DESIGN: This research design includes more than one case, collects data at one particular time, and includes within its research participants groups of people or cases that can be compared.
CROSS-TABULATION: Presentation of data from two variables in one table, enabling the researcher to identify interesting similarities and differences within the data.
CULTURE: Culture is the set of social ideas and behaviours, customs and norms that constitute the way of life of people in a particular society.
CUMULATIVE FREQUENCY: The arrangement of frequency data in categories that add up to 100 per cent.
DATA: A collection of facts (or other information, such as opinions or values) which can be analysed and from which conclusions can be drawn.
DATA PRODUCTION: The way in which social experiences, thoughts, feelings, behaviour and other social phenomena are expressed in words – thus making them available as social data. Individuals and groups can produce data by talking, writing and thinking – using language. This data can then be shared with others using a common language.
DATA SATURATION: The idea that that there are ways in which the researcher can be sure that ‘enough’ research has been done.
DECILE: One-tenth part of a sample or data set.
DEGREES OF FREEDOM: A statistical measure used with chi-squared tests to calculate statistical significance.
DEPENDABILITY: A measure of research quality, meaning, for example, that all data is included, and that no data is lost through unreliable audio recorders or inaccurate transcribers.
DIAGRAM: Presentation of data or findings in a graphical format.
DISCOURSE: Text, either spoken or written, in any medium.
DISCOURSE ANALYSIS: A language-based or linguistic method of qualitative analysis.
DISSEMINATION: The process of spreading the news of research findings so that they become known to a wider audience.
DISTRIBUTION: An arrangement of the values of a variable showing their observed frequency of occurrence.
DOCUMENTS: Written records about people and things that are generated through the process of living. This includes things like film, audio tape or video, but excludes such things as oral histories.
DROP-DOWN LISTS: On an electronic questionnaire, a set of possible answers presented as a list from which respondents select one or more applicable responses.
ELECTRONIC QUESTIONNAIRE: A questionnaire that is designed by the researcher, and completed by the participant, via computer-mediated communication (CMC).
EPISTEMOLOGY: The theory of knowledge and how we know things.
ETHICS: Ethics can be throught of as a set of rules by which individuals and societies maintain moral standards in their lives.
ETHNOGRAPHY: A research strategy in which the researcher spends time (sometimes a number of years) immersed within the research context, seeing and hearing the data at first hand.
EVALUATION: A research strategy that usually relates to an intervention or change that has been made, and whether the intervention has achieved the change or outcomes that were intended.
EXPERIMENTAL GROUP: In a research design, the group of people or materials that are manipulated or changed in some way.
EXPERIMENTAL RESEARCH DESIGN: This type of research assumes that the material or cases that are being studied can be manipulated by the researcher in some way so that some change or difference can be measured.
EXPLANATORY RESEARCH: Research that aims to explain why people experience or understand a social phenomenon in a particular way.
EXPLORATORY RESEARCH: Research that aims to discover what participants think is important about the research topic.
FACE TO FACE: Research methods which involve researcher and participant meeting in person.
FILTER QUESTIONS: Questions that are used to help people to find their own way through a questionnaire, and to select respondents according to whether a question is relevant to them.
FOCUS GROUP: A data collection method that usually brings together a group of between 5 and 13 people who have something in common, which is connected to the research topic, to take part in a discussion on that topic, which is facilitated by the researcher.
FREQUENCY: The number of times that each answer has been given, or that a particular outcome occurs.
GENERALISABILITY: A measure of research quality in which the researcher asks ‘How far am I able to claim that the results or findings from my research are true for or relevant to the wider population or a different context?’ (also known as transferability).
GRAMMAR: The ‘rules’ that control the way that language is structured and, in the case of writing, govern the use of punctuation and syntax so that the writer’s meaning will be clear to the reader.
GREY LITERATURE: Documents that are produced by (and for) organisations or companies.
GROUNDED THEORY: A systematic research approach in which theory is developed – or generated – from data.
HARMONISED DATA: Data gathered from a range of different sources but which take account of the differences in the way the data has been collected, enabling researchers to access comparative data.
HIDDEN OR INVISIBLE POPULATION: Groups who are not easy to identify.
HISTOGRAM: A chart showing the frequency of a ratio or interval variable where the values can be continuous; each bar in the histogram is centred around the mid point or value of the category it represents.
HYPOTHESIS: A proposal or statement that is intended to explain observations or facts; it can be thought of as an ‘informed guess’ about the social world that, if true, would explain the phenomenon being researched.
INDUCTIVE APPROACH: A data collection and analysis approach that works with the data in the form it is observed, heard and recorded.
INFORMANT INTERVIEWS: A type of interview in which the participant is in control of the interview, and is able to tell their own story, in their own way.
INFORMATION: Knowledge gained through study, experience or instruction: what we are told.
INFORMED CONSENT: Making sure that the people who are going to take part in the research understand what they are consenting to participate in.
INTERPRETIVISM: An epistemological position that prioritises people’s subjective interpretations and understandings of social phenomena and their own actions.
INTERPRETIVIST APPROACH: This usually means that qualitative data is collected, with a focus on how people interpret the social world and social phenomena and enabling different perspectives to be explored.
INTERVIEW: A data collection method based around a conversation between two or more people. Interviews usually facilitate direct communication between two people, either face to face or at a distance via telephone or the internet and enable the interviewer to elicit information, feelings and opinions from the interviewee using questions and interactive dialogue.
INTERVIEW GUIDE: An agenda for an interview with additional notes and features to aid the researcher.
KEYWORDS: Terms that tell a database (such as a library catalogue, or a citations search engine) what to look for.
KNOWLEDGE: (1) Information about or awareness of something, an issue, a fact. (2) A understanding of a matter, a fact, an issue.
LIFE HISTORY APPROACH: A data collection method where participants are asked to tell their life story focusing on common events.
LONGITUDINAL STUDY: A research design that enables the researcher to look at the same people or situations at key points in time and to consider how the changes over time have affected different groups of people.
MACRO THEORIES: Theories that attempt to cover all aspects of the social world in general terms (also known as grand theories).
MEAN: A statistical average calculated by totalling all the values and dividing by the number of cases.
MEDIAN: A statistical average calculated by arranging all the values in a sample in numerical order, then noting the middle value of the distribution.
MEMO: A way of recording, thinking about and analysing data, or flagging a piece of data for later investigation.
MESO THEORIES: Middle-level theories relating to social phenomena usually found, such as organisations, institutions, community and family.
MICRO THEORIES: Local theory relating to a specific area, group of people or aspect of the social world.
MIXED METHODS: Methods that combine qualitative and quantitative methods in a way that is best for a specific research project.
MODE: A statistical average calculated by noting the most common value in the distribution.
MULTI-CODED QUESTION: A question that asks for more than one answer, and to which more than one variable is attached.
MULTIVARIATE ANALYSIS: The analysis of three or more variables together.
NARRATIVE: The depiction of a sequence of past events as they appear in present time to the narrator, after they have been processed, analysed and constructed into stories.
NATURAL SCIENCES: The study of the physical world and associated phenomena, including such disciplines as chemistry, physics, etc.
NEGATIVE CASES: Instances that seem to contradict or disprove the emerging theory.
NODE: The term used in the NVivo program to refer to codes.
NON-RESPONSE: This occurs wherever an invited participant declines to be involved in a research project, perhaps because they refuse, are ill or are inappropriate.
NORMAL DISTRIBUTION: Data that is distributed symmetrically around the mean point in a ‘bell shape’.
OBJECTIVISM: An ontological position which asserts that the social phenomena that make up our social world have an existence of their own, apart from and independent of the social actors (humans) who are involved.
OBSERVATION: (1) The collection of data through the use of human senses. (2) The act of watching social phenomena in the real world and recording events as they happen. In research, observation is usually divided into participant observation and simple observation.
ONLINE SOCIAL RESEARCH: The computer-mediated collection of data and typically adapts traditional data collection methods, for example, questionnaires, interviews, focus groups, etc., for use in an online virtual environment.
ONTOLOGY: The ‘science or study of being’; in social research, ontology refers to the way the social world is seen to be and what can be assumed about the nature and reality of the social phenomena that make up the social world.
OPEN CODING: In Grounded Theory data analysis, this is the first stage of coding data, identifying and describing research phenomena, and assigning them appropriate names.
OPEN QUESTIONS: Questions that allow the respondent to answer the question in their own way.
OPERATIONAL DEFINITIONS: Definitions that the researcher can work with and adapt to help to focus the research questions and to decide what data to gather to address those questions.
OVERT METHODS: Open methods of investigation in which participants are aware that they are part of your research.
PARADIGM: A cluster of beliefs and dictates that for scientists in a particular discipline, influence what should be studied, how research should be done, how results should be interpreted and so on.
PARTICIPANT INTERVIEWS: A type of interview in which the researcher is in control of the interview, asking a set of questions to which the research participant replies.
PARTICIPANT OBSERVATION: A data collection method in which the researcher/observer achieves intimate knowledge of the group of people who are the subject of the research, in the group’s natural setting.
PEER REVIEW: In academic settings, the process by which articles and papers are reviewed and selected for publication.
PILOT-TEST: A trial run or an opportunity to try out a data collection method on a small sample of cases before the main research data gathering takes place; question wording, research participant understanding and data collection procedures can all be tried out and amended if necessary, before the main research stage.
PLAGIARISM: Presenting someone else’s work as of it was your own; copying; failing to reference or otherwise attribute the origin.
PLANNING: To arrange in advance (an action or proposed proceeding); to devise, contrive, or formulate (a project or manner of proceeding).
POPULATION: In statistical terms, population refers to the total number of cases that can be included as research subjects.
POSITIVISM: An epistemological position which asserts that knowledge of a social phenomenon is based on what can be observed and recorded rather than subjective understandings.
POSITIVIST APPROACH: This usually means that quantitative data is collected; aspects of the social world, social phenomena, are measured; causal relationships between different aspects of the social world are sought; and large data sets and statistical analysis are often used.
PRIMARY DATA: The data that a researcher gathers specifically for their own research.
PROBABILITY SAMPLE: A sample that can be shown to be highly representative of the whole population – or all the potential cases – in terms of relevant criteria.
PROCESS: An on-going, often continuous series of actions intended to achieve a specific result. This often requires the researcher to follow an established set of (usually) routine procedures.
PROSPECTIVE LONGITUDINAL STUDIES: Research studies that are initially designed to be longitudinal.
PROXY DEFINITION: A ‘rule of thumb’ definition which stands in for a more detailed and sophisticated way of defining something.
PURPOSIVE SAMPLE: A sample of selected cases that will best enable the researcher to explore the research questions in depth.
QUALITATIVE RESEARCH METHODS: Methods that are primarily concerned with stories and accounts including subjective understandings, feelings, opinions and beliefs.
QUANTITATIVE RESEARCH METHODS: Methods that are primarily concerned with gathering and working with data that is structured and can be represented numerically.
QUARTILE: One-quarter part of a sample or data set.
QUASI-EXPERIMENT: Literally, ‘almost the same as an experiment’ but lacking some of the attributes of an experiment.
QUASI-EXPERIMENTAL RESEARCH DESIGN: A research design used in situations where two or more ‘naturally’ different groups of participants or data can be identified, and one used as the control and the other as the experimental group.
QUESTIONNAIRE: (1) A set of questions each with a range of answers; (2) a format which enables standardised, relatively structured, data to be gathered about each of a (usually) large number of cases.
QUINTILE: One-fifth part of a sample or data set.
QUOTA SAMPLING: A sampling technique that selects a certain number, or quota, of cases, on the basis of their matching a number of criteria.
RANDOM CONTROLLED STUDY: A research design that divides the research participants into broad groups relating to age, gender or ethnicity or other characteristics that are relevant to the research topic, and then randomly allocates people to control and experimental groups.
RANDOM SAMPLE: A sample selected from a population where every case has an equal chance of being included in the sample and the composition of the sample cannot be predicted.
RAW DATA: Data that has not been analysed in any way, but is presented in the form it was collected in.
REALISM: (1) An ontological position which asserts that the social world has a reality that is separate from the social actors involved in it, that can be known through the senses as well as the effects of ‘hidden’ structures and mechanisms. (2) An epistemological approach that asserts that knowledge of a social phenomenon is based on both what can be observed and recorded and ‘hidden’ structures and mechanisms whose effects can be observed.
REFLEXIVE DATA: The data produced by individuals themselves as they think about what they are doing, experiencing and feeling and try to understand their social reality.
RELIABILITY: A measure of research quality, meaning that another researcher would expect to obtain the same findings if they carried out the research in the same way, or the original researcher would expect to obtain the same findings if they tried again in the same way.
REPLICABILITY: A measure of research quality, meaning that another researcher would expect to obtain the same findings if they carried out the research in the same way.
REPRESENTATIVE SAMPLE: A sample that has been selected in order to be representative of a wider population.
RESEARCH PROPOSAL: A document that outlines what a research project is about, how it will be undertaken, why it is worthwhile, how long it will take, and why it should be funded.
RESEARCH QUALITY: The reliability, validity, credibility and ethical practice of a piece of research.
RESEARCH QUESTION: The initial enquiry from which a research project develops.
RESEARCH TOOL: Something used to collect data, e.g. a questionnaire, the researcher her/himself or an interview schedule.
RETROSPECTIVE LONGITUDINAL STUDY: A type of longitudinal study where data is available from the past, for example, where participants can be asked to provide data about their past experiences, or where records may be available.
SAMPLING ERROR: The likely variation of the sample means from the population mean.
SAMPLING FRAME: A list of all the members of a population from which a sample may be drawn.
SCATTERGRAM: A graph that plots two variables to show visually whether and how the variables may be related to each other.
SECONDARY DATA: The data that a researcher uses which has already been produced by others.
SELECTIVE CODING: In Grounded Theory data analysis, this is the third and final stage of coding data, and is the process of choosing a central or ‘core’ category and then relating all the other codes, themes and categories to it.
SEMI-STRUCTURED: Describes data, or a data collection method (such as an interview or questionnaire), in which questions and answers may vary in wording and length; answers to questions are often in the respondent’s own words.
SIMPLE OBSERVATION: A data collection method in which the researcher/observer is not part of the process that is being researched, but is an objective outsider.
SNOWBALL SAMPLING: A sampling technique where members of an initial sample are asked to identify others with the same characteristics as them, who the researcher then contacts.
SOCIAL PHENOMENON: Anything that influences or is influenced by human beings who interact with and are responsive to each other.
SOCIAL WORLD: The setting or cultural surroundings in which social research takes place.
STANDARD DEVIATION: A statistical measure of how values or cases are distributed around the mean value or case.
STATISTICAL SAMPLING: The process of selecting a probability sample.
STATISTICAL SIGNIFICANCE: A measure of the probability that the relationships found in a sample will also be found in the wider population.
STATISTICS: Data that is structured and can be counted or is already expressed in numerical terms.
STRATIFICATION: A method of organising a population in order to improve the representativeness of a sample.
STRATIFIED SAMPLE: A sample that is selected to ensure that certain categories and groups of people and cases are included, proportionate to their presence in the population.
STRUCTURED: Describes data, or a data collection method (such as an interview or questionnaire), in which the questions are the same for each participant, and typically there is a common set of answers for each question.
SUBSIDIARY RESEARCH QUESTIONS: These are questions that help you to specify more precisely the areas of the research topic that you will focus on.
SYNCHRONOUS COMMUNICATION: Communication between people where all communicants are taking part at the same time and can ‘chat’; also known as real-time communication.
THEMATIC ANALYSIS: A process of working with raw data to identify and interpret key ideas or themes.
THEORETICAL FRAMEWORK: The ideas and approaches to viewing and gathering knowledge, and which provide the basic ways of addressing a topic.
THEORETICAL MEMOING: In Grounded Theory data analysis, ‘the theorizing write-up of ideas about substantive codes and their theoretically coded relationships as they emerge during coding, collecting and analyzing data, and during memoing’ (Glaser).
THEORETICAL SAMPLE: A sample of selected cases that will best enable the researcher to explore theoretical ideas.
THEORETICAL SAMPLING: A sampling technique in which the initial cases are usually selected on a relatively unstructured basis: as ‘theory’ begins to emerge from the initial data, further cases are selected to explore and test the emerging theory; this continues until there is no new theory emerging and theoretical ‘saturation’ is reached.
THEORY: A set of ideas or related concepts that can be used to explain and understand an event, situation, social phenomena.
TOPIC GUIDE: A set of questions, key points or prompts to be included in a focus group or interview that helps the facilitator to remember the issues/questions to introduce; suggests ways of approaching topics and phrasing questions; reminds the facilitator to probe and follow up comments; includes an introduction and a way of ending; if you are holding more than one focus group or two or more facilitators are involved ensures that the same topics are covered in each group.
TRANSFERABILITY: A measure of research quality in which the researcher asks ‘How far am I able to claim that the results or findings from my research are true for or relevant to the wider population or a different context?’ (also known as generalisability).
TRANSPARENT: In a research context, this means that the research process and the decisions made by the researcher are recorded and available to others for scrutiny.
TRIANGULATION: A measure of research quality, meaning that if different types of data are collected to address the same research question, each set of data can be used to check the findings from the others.
TYPOLOGY: A typical model of the way variables tend to be found in relation to each other.
UNDERSTANDING: Grasping the meaning of information.
UNIT: The individual respondent or subject about whom a researcher collects data, for example countries, universities, families or individuals.
UNSTRUCTURED: Describes data, or a data collection method (such as an interview or questionnaire), in which questions and answers do not follow a guide or template.
VALIDITY: A measure of research quality, meaning that the data we are planning to gather and work with to address our research questions is a close representation of the aspect of social reality we are studying.
VALUE STATEMENTS: Statements, usually from an individual, that are indications of each person’s opinion where they are using their own judgement and criteria.
VARIABLE: An attribute or characteristic of cases (for example, individuals, organisations, objects or situations) which can vary from case to case.
VIRTUAL COMMUNITIES: Groupings of people who share some experience but meet virtually online rather than face to face.
Source: Bob Matthews and Liz Ross, RESEARCH METHODS A practical guide for the social sciences (England: Pearson Education Limited 2010)