B

b weight
The amount by which a criterion variable will increase for a one-unit increase in a predictor variable; a predictor’s coefficient in the multiple regression equation.

Back translation
System of translating a psychological scale from language A into language B and then back to language A again to ensure equivalence.

Backward hierarchical downwards log-linear analysis
Removing interactions from a saturated log-linear model moving towards one-way effects.

Bar chart
Chart in which (usually) the x-axis represents a categorical variable and the y-axis can represent frequency, average, percentage, etc.

Baseline measure
Measure of what would occur if no experimental level of the independent variable were applied; how ‘untreated’ participants perform.

Beta value
Standardised b weights (i.e., as expressed in standard deviations).

Between conditions variation
Variation, calculated in a repeated measures design, which comes from how scores vary between the conditions with the between subjects variance accounted for.

Between groups ANOVA
ANOVA analysis where only unrelated factors are involved.

Between groups sum of squares
Sum of squares of deviations of sample means from the grand mean.

Between groups variance
Variance of sample means around grand mean.

Between subjects variance
The variance among data attributable to variation among the participants’ overall performances.

Bibliography
A list of sources used, but not cited, in the preparation of an essay or report. Not required in psychology reports.

Bi-modal distribution
Data set with two modes.

Binomial sign test (S)
Nominal-level test for difference between two sets of paired/related data using direction of each difference only.

Biserial (correlation coefficient)
Correlation used where one variable is artificially dichotomous; formed by categorising from an underlying continuous and normal distribution.

Bonferroni t tests
Procedure for testing means pairwise, which involves raising the critical values of t.

Box-plot
Exploratory data chart showing median, central spread of data and position of relative extremes.

C

Capitalising on chance
Making too many tests with α set at .05 on the same data, hence increasing the likelihood of a Type I error.

Categorical variable
Variable where cases are merely placed into independent, separate categories.

Ceiling effect
Occurs where measure produces most values near the top end of a scale.

Census
Survey of whole population.

Central limit theorem
Used in the theoretical estimation of the standard error of a sampling distribution from the standard deviation of a sample.

Central tendency
Formal term for any measure of the typical or middle value in a group.

Chi-square (χ²)
Statistic used in tests of association between two unrelated categorical variables. Also used in goodness-of-fit test, log-linear analysis and several other tests.

Chi-square change
Change in chi-square as interactions are removed from the saturated model in log-linear analysis.

Class intervals
Categories into which a continuous data scale can be divided in order to summarise frequencies.

Clinical method
Interview method using structured questions but may be tailored in response to interviewee’s answers; seeks to test specific hypothesis.

Closed questions
Question with only a specified set of responses that the respondent can choose from, e.g., ‘yes/no’.

Code (coding)
Quantifying by giving similar observed instances of behaviour a symbol.

Coding
Giving ‘dummy’ numbers to discrete levels of an independent variable.

Coding unit
Item categories identified in qualitative data using content analysis.

Cohort
Large sample of people, often children of the same age, identified for longitudinal or cross-sectional study.

Cohort effect
Confounding in cross-sectional study when two different age groups have had quite different experiences.

Collaborative research
Research in which participants are fully involved to the extent of organising their own processes of research and change. Researcher as consultant.

Collectivist
System of social norms and beliefs in which the individual’s needs and aspirations are subsidiary to those of the group, often the family. Duty and responsibility to others rule over independence and self-seeking goals.

Collinearity
Extent of correlations between predictor variables in multiple regression.

Confidence limits/intervals
Estimated limits (e.g., ‘with 95% confidence’) to the likely range (interval) within which a population mean lies, based on an estimate from a sample mean and standard error.

Confidentiality
Keeping data from participants or clients away from publication.

Confounding variable
Variable that is uncontrolled and obscures any effect sought, varying with the independent variable in a systematic manner.

Constant comparative analysis
Regular checking of the emergent category system (in GT) with raw data and sub-categories in order to rearrange and produce the tightest fit.

Constructivism
Theory holding knowledge to be relative and ‘facts’ to be social constructions, not permanent realities.

Content analysis
Search of qualitative materials (especially text) to find ‘coding units’ (usually words, phrases or themes); analysis often concentrates on quantitative treatment of frequencies but can be a purely qualitative approach.

Contextualist constructionist
Theory of knowledge (epistemological position), which sees knowledge and truth as relative; different versions are possible depending on the context in which knowledge claims are made.

Continuous scale/variable
Scale where there are no discrete steps; theoretically, all points along the scale are meaningful.

Control group
Group used as baseline measure against which the performance of the experimental group is assessed.

Co-operative enquiry
Investigation involving researcher and participants working together.

Correlation
A (standardised) measure of relationship of co-variance between two variables.

Coefficient
Number signifying strength of correlation between two variables.

Curvilinear
Correlation between two variables with low r value because the relationship does not fit a straight line but a good curve.

Negative
Correlation where, as values of one variable increase, related values of another variable tend to decrease.

Positive
Correlation where, as values of one variable increase, related values of another variable also tend to increase.

Correlational study
Study of the extent to which one variable is related to another, often referring to non-manipulated variables measured outside the laboratory.

Counterbalancing
Half participants do conditions in a particular order and the other half take the conditions in the opposite order – this is done to balance possible order effects.

Co-variate
A variable that correlates with a dependent variable on which two groups differ and which can be partialled out using ANCOVA.

Cramer’s phi or V
General statistic used to estimate effect size in chi-square analyses.

Criterion/target/dependent variable
Variable on which values are being predicted in regression.

Critical value
Value that the result of the test statistic (e.g., z) must reach in order for the null hypothesis to be rejected.

Cross-cultural study
Comparative study of two or more different societies, or social/ethnic sub-groups.

Cross-generational
Confounding occurring when one longitudinally studied group is compared with another that has generally had quite different social experiences.

Cross-lagged

Cross-sectional
Comparative study of several cross-sectional groups taken at intervals in the short term, over a relatively short period (say, two or three years) longitudinal study.

Cross-tabs table
Term for table of frequencies on levels of a variable by levels of a second variable.

Cultural relativity
View that a person’s behaviour and characteristics can only be understood through that person’s own cultural environment.

Cumulative frequency
Distribution (table or chart) that shows the number of cases that have occurred up to and including the current category.

D

d, Cohen’s
Measure of effect size; used here in calculating power.

Data set
Group of data points or values that can be summarised or analysed.

Data
Relatively uninterpreted information; gathered facts.

Debriefing
Informing participants about the full nature and rationale of the study they’ve experienced, and attempting to reverse any negative influence.

Deception
Leading participants to believe that something other than the true independent variable is involved, or withholding information such that the reality of the investigative situation is distorted.

Deciles
Points on a measured scale that mark off each 10% of the data set or population.

Deduction
Logical argument using rules to derive a conclusion from premises.

Degrees of freedom
Common term in statistical analysis having to do with the number of individual data points that are free to vary given that overall summary values are known.

Delta (δ)
Statistic used to estimate power using effect size.

Demand characteristics
Cues in a study that help the participant to work out what is expected.

Dependent variable (DV)
Variable that is assumed to be directly affected by changes in the independent variable in an experiment.

Derived etic
General/universal psychological construct modified from its origin in one culture after researcher’s immersion in one or more new cultures.

Design
Structure and strategy of a piece of research.

Deviation score/value
Amount by which a particular score differs from the mean of its set.

Diagnostic item
Item not obviously or directly connected to the attitude object, yet which correlates well with overall scores and therefore has discriminatory power and predictive power.

Diary method
Data-gathering method where participant makes regular (often daily) record of relevant events.

Dichotomous variable
Variable with just two exhaustive values (e.g., male/female).

Difference mean
Mean of differences between pairs of scores in a related design.

Directional hypothesis
Hypothesis that states which way a difference or correlation exists – e.g., population mean A > population mean B, or correlation is negative.

Disclosure
Letting people know that they are the object of observation.

Discourse analysis (DA)
Qualitative analysis of interactive speech, which assumes people use language to construct the world; talk is organised according to context and personal stake; it is not evidence of internal psychological processes.

Discrete scale/variable
Scale on which not all subdivisions are meaningful; often one where the underlying construct to be measured can only come in whole units (e.g., number of children).

Discriminatory power
Extent to which an item, or the test as a whole, separates people along the scoring dimension.

Disguise
Feature of questioning approach that keeps respondents ignorant of the aims of the questioning.

Dispersion
Technical and general term for any measure of the spread of values in a sample of data or population.

Distribution dependent test
Significance test using estimations of population parameters.

Distribution free test
Significance test that does not depend on estimated parameters of an underlying distribution.

Distribution
Shape and spread of data sets/populations.

Double blind
Experimental procedure where neither participants nor data gatherers/assessors know which treatment participants have received.

E

Effect
A difference or correlation between samples leading to an assumed relationship between variables in the population.

Effect size
The size of the effect being investigated (difference or correlation) as it exists in the population.

Emergent theory
Theory that emerges from data as they are analysed; not based on prior research literature.

Emic
Psychological construct applicable within one or only a few cultures.

Empirical method
Scientific method of gathering information and summarising it in the hope of identifying general patterns.

Enlightenment
Tendency for people to be familiar with psychological research findings.

Epistemology
Theory of knowledge and of how knowledge is constructed.

Epsilon
Statistic calculated for use when the sphericity assumption is violated; df are multiplied by this statistic in order to reduce them and avoid Type II errors.

Equal probability selection method (epsem)
Procedure for producing a sample into which every case in the target population has an equal probability of being selected.

Error between subjects
Error term associated with the between groups portion of the sum of squares division in a mixed ANOVA design.

Error rate per comparison
Given the significance level set, the likelihood of a Type I error in each test made on the data if H0 is true.

Error sum of squares
Sum of squares of deviations of each score from its own group mean (also: within groups SS).

Error variance
Total variance of all scores from their group means, caused by the operation of randomly acting variables (also: within groups variance).

Error within subjects
Error term associated with the within subjects portion of the sum of squares division in a mixed design.

Eta-squared Η²
Measure of effect size.

Ethnocentrism
Bias of viewing and valuing another’s culture from one’s own cultural perspective.

Etic
Universal psychological construct, applicable to all cultures.

Evaluation apprehension
Participants’ concern about being tested, which may affect results.

Event coding
Recording pre-specified behavioural events as they occur.

Expected frequencies
Frequencies expected in table if no association exists between variables – i.e., if the null hypothesis is true.

Experiment
Study in which an independent variable is manipulated under strictly controlled conditions.

Experimental designs

Factorial design
Experiment in which more than one independent variable is manipulated.

Independent samples (between groups; one group of participants groups/subjects independent/unrelated)
Each condition of the independent variable is experienced by only.

Matched pairs
Each participant in one group/condition is paired on specific variable(s) with a participant in another group/condition.

Repeated measures (within subjects/groups)
Each participant experiences all levels of the independent variable.

Related
Design in which individual scores in one condition can be paired with individual scores in other conditions.

Single participant
Design in which only one participant is tested in several trials at all independent variable levels.

Small N design
Design in which there is only a small number of participants, typically in clinical or counselling work but also where participants need substantial training for a highly skilled task.

Unrelated
Design in which individual scores in one condition cannot be paired (or linked) in any way with individual scores in any other condition.

Experimental realism
Effect of attention-grabbing, interesting experiment in compensating for artificiality or demand characteristics.

Experimenter expectancy
Tendency for experimenter’s knowledge of what is being tested to influence the outcome of research.

Exploratory data analysis
Close examination of data by a variety of means, including visual display, before submitting them to significance testing; recommended by Tukey.

Extraneous variable
Anything other than the independent variable that could affect the dependent variable; it may or may not have been allowed for and/or controlled.

F

F test/ratio
Statistic giving ratio of between groups to within groups variance.

Face-to-face
Interview in which researcher and interviewee talk together in each other’s presence.

Factor
Independent variable in a multi-factorial design.

Factor analysis
Statistical technique, using patterns of test or sub-test correlations, that provides support for theoretical constructs by locating correlational ‘clusters’ and identifying explanatory factors.

Factorial ANOVA
Design involving the analysis of the effects of two or more factors (independent variables) on differences between group means.

Falsifiability
Principle that theories must be defined in a way that makes it possible to show how they could be wrong.

Family-wise error rate
The probability of making at least one Type I error in all the tests made on a set of data, assuming H₀ is true.

Field experiment
Experimentally designed field study.

Field study
Study carried out outside the laboratory and usually in the participants’ normal environment.

Fishing
Term used to describe situation where a student/researcher uses a lot of measures and investigates results to see if there are any significant differences or correlations. Frowned upon because it is likely to generate many Type I errors.

Floor effect
Phenomenon where measure produces very many low scores.

Focus group
Group, often with common interest, who meet to discuss an issue in a collective interview.

Frequency data/ Frequencies
Numbers of cases in specific categories.

Frequency distribution
Distribution showing how often certain values occur.

Frequency polygon
Histogram showing only the peaks of class intervals.

Frequency
How often a certain event (e.g., score) occurs.

Friedman’s (χ²) test
Non-parametric rank test for significant differences between two or more related samples.

G

Goodness of fit
Test of whether a distribution of frequencies differs significantly from a theoretical pattern.

Grand mean
Mean of all scores in a data set, irrespective of conditions or groups.

Grounded theory (GT)
Theory driving the analysis of qualitative data in which patterns emerge from the data and are not imposed on them before they are gathered.

Group difference study
A study that compares the measurement of an existing variable in two contrasting groups categorised by long-term or inherent characteristics such as sex, gender, ethnicity, personality, social class and so on.

H

Halo effect and reverse halo effect, devil effect, horns effect
Tendency for people to judge a person’s characteristics as positive if they have already observed one central trait to be positive or have gained an overall positive first impression. Reverse effect occurs if an initial negative impression causes traits to be assessed negatively.

Hawthorne effect
Effect on human performance caused solely by the knowledge that one is being observed.

Heteroscedasticity
Degree to which the variance of residuals is not similar across different values of predicted levels of the criterion in multiple regression.

Hinge position
For constructing a box-plot, the position from the bottom of the data set where the first quartile falls and the position from the top of the data set where the third quartile falls.

Hinge spread
On a box-plot, the distance between the lower and upper hinges.

Histogram
Chart containing whole of a continuous data set divided into proportional class intervals.

Homogeneity of variance
Situation where sample variances are the same or similar.

Hypothesis
Precise statement of assumed relationship between variables.

Hypothesis-testing
Research that analyses data for a predicted effect.

Hypothetical construct
Phenomenon or construct assumed to exist, and used to explain observed effects, but as yet unconfirmed; stays as an explanation of effects while evidence supports it.

Hypothetico-deductive
Method of recording observations, developing explanatory theories and testing predictions from those theories.

I

Idiographic
Approach that emphasises unique characteristics and experiences of the individual, not common traits.

Imposed etic
Psychological construct from researcher’s own culture, applied to a new culture without modification.

Independent variable (IV)
Variable which experimenter manipulates in an experiment and which is assumed to have a direct effect on the dependent variable.

Individualistic
System of social norms and beliefs where individual needs and goals dominate over responsibility to others. The self is paramount and independence from others is a primary value.

Induction
Process of moving from particular instances to a generalised pattern.

Inductive analysis
Work with qualitative data, which permits theory and hypotheses to evolve from the data rather than hypothetico-deductive testing of hypotheses set before data are obtained.

Inferential test/statistics
Procedures for making inferences about whole populations from which samples are drawn, e.g., significance tests.

Informed consent
Agreement to participate in research in the full knowledge of the research context and participant rights.

Interaction effect
Significant effect where effect of one factor is different across levels of another factor.

Inter-observer reliability
Extent to which observers agree in their rating or coding.

Interpretive phenomenological analysis (IPA)
Approach that attempts to describe an individual’s experiences from their own perspective as closely as possible, but recognises the interpretive influence of the researcher on the research product.

Interquartile range
Distance between first and third quartile in a distribution.

Interval coding
Recording what behaviour is occurring, or the typical behaviour, in specified time intervals.

Intervention
Research that makes some alteration to people’s lives beyond the specific research setting, in some cases because there is an intention to ameliorate specific human conditions.

Involuntary participation
Taking part in research without agreement or knowledge of the study.

L

Leptokurtic distribution
Non-normal distribution that is closely bunched in the centre and tall.

Levels (of the IV)
The different values taken by the independent variable; often, the conditions of an experiment, e.g., levels of caffeine at 50mg, 100mg and 200mg in the investigation of memory recall.

Levels of measurement
Levels at which data are categorised or measured.

Interval
Level of measurement at which each unit on a scale represents an equal change in the variable measured.

Nominal
Level of measurement at which numbers are only labels for categories.

Ordinal
Level of measurement at which cases are arranged in rank positions.

Quasi-interval
Scale that appears to be interval but where equal intervals do not necessarily measure equal amounts of the construct.

Ratio
Interval-type scale where proportions on the scale are meaningful; usually an absolute zero exists.

Likelihood ratio chi-square
Type of chi-square statistic used in log-linear analysis.

Line chart
Chart joining continuous data points in a single line.

Linear coefficients
Values to be entered into an equation for calculating linear contrasts.

Linear contrasts
Procedure for testing between individual pairs of means or combinations of means, a priori (i.e., predicted).

Linear regression
Procedure of predicting values on a criterion variable from a predictor or predictors using correlation.

Linearity
Extent to which a relationship between two variables can be represented by a straight line rather than, say, a curved line.

Literature review
A review of relevant literature on the topic of the report. This must be used in the argument towards the hypotheses, predictions or aims.

Log-linear analysis
Analysis similar to chi-square but which will deal with three-way tables or greater.

Log-linear model
A theoretical and statistical structure proposed to explain cell frequency variation in a multi-way frequency table.

Longitudinal study
Comparative study of one individual or group over a relatively long period (possibly including a control group).

Lower hinge
On a box-plot, the first quartile.

M

Main effect
In a multi-factorial ANOVA analysis, the effect of one factor across all its levels, irrespective of any other factors.

Mann-Whitney U test
Ordinal-level significance test for differences between two sets of unrelated data.

MANOVA
Statistical procedure using ANOVA on more than one dependent variable.

Marginals
The total of each column and row, and the overall total of frequencies, in a cross-tabs table.

Mauchly’s test
Test of sphericity calculated in SPSS.

Mean (arithmetic)
Average of values found by adding them all and dividing by the number of values in the set.

Mean deviation
Measure of dispersion – mean of all absolute deviations.

Mean sum of squares
Sum of squares divided by df.

Measured variable
Variable where cases measured on it are placed on some sort of scale that has direction.

Median
Measure of central tendency; middle value of data set.

Median position/location
Position where median is to be found in an ordered data set.

Median split method
Dividing a set of measured values into two groups by dividing them into high and low at their median.

Meta-analysis
Statistical analysis of results of multiple equivalent studies of the same, or very similar, effects in order to assess validity more thoroughly.

Mixed design ANOVA
ANOVA analysis where both related and unrelated factors are involved.

Mixed methods
An emerging school of thought that promotes research where qualitative and qualitative methods are used together to answer for different aspects of the research question.

Mode/modal value
Measure of central tendency – most frequent value in a data set.

Multiple correlation coefficient
Value of the correlation between several combined predictor variables and a criterion variable.

Multiple regression
Technique in which the value of one ‘criterion’ variable is estimated using its known correlation with several other ‘predictor’ variables.

Mundane realism
Feature of design where experiment resembles everyday life but is not necessarily engaging.

N

Narrative psychology
Research approach that sees human activity as ‘storied’; that is, humans tend to recall and talk about their lives in stories rather than in a logical and factual manner.

Natural experiment
Events beyond researcher’s direct control but where an IV and DV can be identified.

Naturalistic design
Design in which experimenters investigate participants in their everyday environment.

Negative case analysis
Process of seeking contradictions of emergent categories or theory in order to adjust category system to incorporate and explain more of the data.

Negatively skewed
Description of distribution that has a longer tail of lower values.

Newman–Keuls post hoc analysis
Post hoc test of means pairwise; safe so long as number of means is relatively low.

Nomothetic
Approach that looks for common and usually measurable factors on which all individuals differ.

Non-directional hypothesis
Hypothesis that does not state in which direction a difference or correlation exists.

Non-directive interview
Interview in which the interviewer does not direct discussion and remains non-judgmental.

Non-equivalent groups
A possible confounding variable where two or more groups in an independent samples design experiment differ on a skill or characteristic relevant to the dependent variable.

Non-parametric test
Significance test that does not make estimations of parameters of an underlying distribution; also known as a distribution free test.

Normal distribution
Continuous distribution, bell-shaped, symmetrical about its mid-point.

Null hypothesis
Assumption of no effect in the population from which samples are drawn (e.g., no mean population difference or no correlation).

O

Observation types

Controlled
Observation in controlled setting, often a laboratory or observation room.

Indirect/archival
Observations not made on people directly but using available records.

Naturalistic
Observation without intervention in observed people’s own environment.

Participant
Observation in which observer takes part or plays a role in the group observed.

Structured/systematic
Observation that uses an explicitly defined coding framework for data recording.

Observational design
Study that is solely observational and does not include any experimentation.

Observational study
Research which gathers data by watching and recording behaviour.

Observational technique
Procedure using observation in some way and that may or may not be part of an experiment.

Observed frequencies
Frequencies obtained in a research study using categorical variables.

Observer bias
Threat to validity of observational recordings caused solely by characteristics of the observer.

One-tailed test
Test referring to only one tail of the distribution under H0; may be used if the alternative hypothesis is directional (but controversial).

Open-ended questions
Type of interview/questionnaire item to which interviewees respond at length.

Operational definition
Definition of phenomenon in terms of the precise procedures taken to measure it.

Order effect
A confounding effect caused by experiencing one condition, then another, such as practice or fatigue.

Outer fence
Extreme position on a box-plot being, for the lower fence, lower hinge - 1.5 x the hinge spread, and for the upper fence, upper hinge + 1.5 x the hinge spread.

Outliers
Values that fall more than 1.5 times the IQR above or below the most extreme values in the IQR set. Often removed from analysis of data set because they unnecessarily distort statistics, but this procedure must be openly reported.

P

p ≤ .01
Significance level preferred for greater confidence than that given by the conventional one and that should be set where research is controversial or a one-shot-only trial.

p ≤ .05
Conventional significance level.

p ≤ .1
Significance level generally considered too high for rejection of the null hypothesis but where, if p under H0 is this low, further investigation might be merited.

Page trend test
Test for repeated measures design with three or more levels where a specific order of magnitude for all the levels has been predicted, i.e., which one will be highest, next highest and so on.

Pairwise comparison

Panel design
Design in which the same group of participants is tested at the beginning and end of one interval or more.

Panel
Stratified group who are consulted in order for opinion to be assessed.

Paradigm
A prevailing agreed system of scientific thinking and behaviour within which research is conducted.

Paralinguistics
Body movements and vocal sounds that accompany speech and modify its meaning.

Parametric test
Relatively powerful significance test that uses estimations of population parameters; the data tested must usually therefore satisfy certain assumptions; also known as a distribution dependent test.

Partial correlation
Method of finding the correlation of A with B after the common variance of a third correlated variable, C, has been removed.

Participant expectancy
Effect of participants’ expectancy about what they think is supposed to happen in a study.

Participant variables
Person variables (e.g., memory ability) differing in proportion across different experimental groups, and possibly confounding results.

Participant
Person who takes part in a psychological investigation as a member of a sample or individual case.

Participative research
Research in which participants are substantially involved in the investigative process as active enquirers.

Pearson’s product moment correlation coefficient
Parametric measure of correlation.

Percentile
Point on a measured scale that marks off certain percentage of cases in an ordered data set.

Phenomenology
A philosophical approach that concentrates on the study of consciousness and the objects of direct experience. Mental awareness is primary.

Φ (Phi)
Phi statistic for estimating power in ANOVA analyses.

Phi coefficient (Φ)
Statistic used for effect size estimate in a 2 x 2 table after c2 analysis; also:

Phi coefficient
Measure of correlation between two truly dichotomous variables.

Pilot study/trials; piloting
Preliminary study or trials often carried out to predict snags and assess features of a main study to follow.

Placebo group
Group of participants who don’t receive the critical ‘treatment’ but do receive everything else the experimental group receives; used in order to eliminate placebo effects – participants may perform differently simply because they think they have received an effective treatment.

Plagiarism
Claiming that other authors’ work is your own, e.g., by not providing quotation marks or appropriate references. Plagiarism occurs whether or not the writer knew they were using another author’s exact words or structure.

Platykurtic distribution
Non-normal distribution that is widely spaced out and low in the centre.

Pleasing the experimenter
Tendency of participants to act in accordance with what they think the experimenter would like to happen.

Point biserial correlation
Measure of correlation where one variable is truly dichotomous and the other is at interval level.

Pooled variance
Combination of two sample variances into an average in order to estimate population variance.

Population
All possible members of a category from which a sample is drawn.

Population parameter
Statistical measure of a population (e.g., mean, standard deviation).

Positively skewed
Description of distribution that contains a longer tail of higher values.

Positivism
Methodological belief that the world’s phenomena, including human experience and social behaviour, are reducible to observable facts and the mathematical relationships between them. Includes the belief that the only phenomena relevant to science are those that can be measured.

Post facto research
Research where pre-existing and non-manipulated variables among people are measured for difference or correlation.

Post hoc comparisons/tests
Tests between means, or groups of means, conducted after inspection of data from initial analysis.

Power
1- β. The probability of not making a Type II error if a real effect exists; the probability of obtaining a case or sample above the level cut off by β in the population defined by the alternative hypothesis.

Power efficiency
Comparison of the power of two different tests of significance.

Predictor
Variable used in combination with others to predict values of a criterion variable in multiple regression.

Pre-test
Measure of participants before an experiment in order to balance or compare groups, or to assess change by comparison with scores after the experiment.

Primary reference
An original source that the writer has not read but about which they have obtained information in a secondary source.

Probability
A numerical measure of pure ‘chance’ (randomly based) occurrence of events.

Empirical
A measure of probability based on existing frequencies of occurrence of target events.

Logical
A measure of probability calculated from logical first principles.

Probability distribution
A histogram of the probabilities associated with the complete range of possible events.

Probe
General request for further information used in semi-structured interview.

Prompt
Pre-set request for further information used in semi-structured interview if the information is not offered spontaneously by interviewee on a particular item.

Psychometric test
Test that attempts to quantify through measurement psychological constructs such as skills, abilities, character, etc.

Psychometrist/psychometrician
Person who creates and is a specialist with psychometric tests.

Psychometry
The technology of test creation for the quantification of psychological constructs.

Q

Qualitative approach
Methodological stance gathering qualitative data which usually holds that information about human events and experiences, if reduced to numerical form, loses most of its important meaning for research.

Qualitative data
Data left in their original forms of meaning (e.g., speech, text) and not quantified in numerical form.

Quantitative approach
Methodological stance gathering quantitative data following a belief that science requires accurate measurement and quantitative data.

Quantitative data
Data in numerical form, i.e., counts or measurements, the results of measurement or counting.

Quartiles
Points on a measured scale that mark the 25th, 50th and 75th percentiles of a distribution.

Quasi-experiment
Experiment in which experimenter does not have complete control over all central variables.

R

Radical constructionist
Theory of knowledge (epistemological position) that sees knowledge and truth as semantic construction.

Random error
Any error possible in measuring a variable, excluding error that is systematic.

Random number
Number not predictable from those preceding it.

Randomisation
Putting stimulus items or trial types into random order for the purpose of elimination of order effects.

Randomise
To put the trials of, or stimuli used in, an experiment into an unbiased sequence, where prediction of the next item is impossible.

Randomly allocate
To put people into different conditions of an experiment on a random basis.

Range
Measure of dispersion – top to bottom value (plus one).

Range restriction
A selection of cases from a larger potential data set, which has the effect of distorting the true population correlation.

Raw data/scores
Untreated, unconverted values obtained directly from measuring process used in a study.

Reactive study/design

Realism
Theory of knowledge holding that there is a unitary reality in the world that can be discovered using the appropriate investigative methods.

Reflexivity
Researchers’ recognition that their personal perspective influences and/or constructs the research interpretation.

Regression coefficient
Amount by which predictor variable values are multiplied in a regression equation in order to estimate criterion variable values.

Regression line
Line of best fit on a scatterplot, which minimises residuals in regression.

Reification
Tendency to treat abstract concepts as real entities.

Rejection region
Area of (sampling) distribution where, if a result falls within it, H0 is rejected; the area cut off by the critical value.

Related t test
Parametric difference test for related data at interval level or above.

Relativism
Theory of knowledge holding that objective facts are an illusion and that knowledge is constructed by each individual through a unique personal framework.

Reliability
Extent to which findings or measures can be repeated with similar results; consistency of measures and consistency of a psychological scale.

Internal
Consistency between the items of a scale or test.

Cronbach’s alpha
A measure of scale reliability using the variance of respondents’ scores on each item in relation to overall variance on the scale.

External (or stability or test-retest method)
Stability of a test: its tendency to produce the same results when tested on the same people at two different times.

Internal
Consistency of a test within itself. Tendency for people to score at the same strength on similar items.

Item analysis
Checking each item in a scale by comparing its relationship with total scores on the scale.

Kuder–Richardson

Split-half
Correlation between scores on two equal parts of a test.

External
Consistency of a test with itself when administered more than once.

Test-retest
Testing of the same group of respondents twice on separate occasions in order to estimate external reliability.

Replication
Repeating a completed study.

Representative design
Extent to which the conditions of an experiment represent those outside the laboratory to which the experimental effect is to be generalized.

Research prediction
Prediction in precise terms about how variables should be related in the analysis of data if a hypothesis is to be supported.

Research question
The question a researcher is trying to answer in an investigation.

Residual (y – yˆ)
Difference between an actual score and what it would be as predicted by a predictor variable or by a set of predictor variables.

Respondent
Person who is questioned in an interview or survey.

Respondent validation/ Member checking
Attempt to validate findings and interpretations by presenting these to original participants for comments and verification.

Response (acquiescence) set
Tendency for people to agree with test items as a habitual response.

Right to privacy
Right that upholds people’s expectation that their personal lives will not be intruded upon by voluntary or involuntary research participation.

Robustness
Tendency of test to give satisfactory probability estimates even when data assumptions are violated.

Role-play
Study in which participants act out given parts.

S

S
See binomial sign test.

Sample
Group selected from population for an investigation.

Biased
Sample in which members of a sub-group of the target population are over- or under-represented.

Cluster
Groups in the population selected at random from among other similar groups and assumed to be representative of a population.

Convenience / Opportunity
Sample selected because they are easily available for testing.

Expert choice
See purposive sample below.

Haphazard
Sample selected from population with no conscious bias (but likely not to be truly random).

Purposive
Non-random sampling of individuals likely to be able to make a significant contribution to the data collection for a qualitative project either because of their specific experiences or because of their expertise on a topic.

Quota
Sample selected, not randomly, but so that specified groups will appear in numbers proportional to their size in the target population.

Representative

Self-selecting
Sample selected for study on the basis of members’ own action in arriving at the sampling point.

Simple random
Sample selected in which every member of the target population has an equal chance of being selected and all possible combinations can be drawn.

Stratified
Sample selected so that specified sub-groups will appear in numbers proportional to their size in the target population; within each sub-group cases are randomly selected.

Systematic (random)
Sample selected by taking every nth case from a list of the target population; ‘random’ if starting point for n is selected at random.

Sample statistic
Statistical measure of a sample (e.g., mean, standard deviation).

Sampling bias (or selection bias)
Systematic tendency towards over- or under-representation of some categories in a sample.

Sampling distribution (of means)
Theoretical distribution that would be obtained by taking the same statistic from many same size randomly selected samples (e.g., the mean).

Sampling error
Difference between a sample statistic and the true population statistic, usually assumed to be random in origin.

Sampling frame
The specified range of people from whom a sample will be drawn. Those within a population who can be sampled.

Saturated model
Model in log-linear analysis that explains all variation in a multi-way frequency table so that chi-square is zero and expected frequencies are the same as observed frequencies.

Saturation
Point in GT work where additional data make only trivial contributions and cannot alter the emerged framework of categories and themes.

Scale value
On a Thurstone scale, the average of judges’ ratings of an item; respondent is given this score if they agree with it.

Scatterplot
Diagram showing placement of paired values on a two-dimensional chart.

Scheffé post hoc analysis
Post hoc test that takes into account all possible comparisons of combinations of means (most conservative post hoc test).

Scientific method
General method of investigation using induction and deduction.

Secondary reference
Source in which the writer obtained information about an original or primary source.

Selective coding
Higher order treatment of initial themes and categories where superordinate themes may emerge that bind lower categories together.

Self-report method
A general term for methods in which people knowingly provide information about themselves.

Semi-interquartile range
Half the distance between first and third quartile in a distribution.

Semi-partial correlation
Correlation between a criterion variable B with the residuals of A, after A has been regressed on C. Removes the common variance of A and C from the correlation of A with B.

Semi-structured interview
Interview with pre-set list of topics but in which an informal conversational tone is attempted and the interviewer ‘plays it by ear’ as to whether sufficient information has been provided by the interviewee.

Sign test
See binomial sign test.

Significance levels
Levels of probability at which it is agreed to reject H0. If the probability of obtained results under H0 is less than the set level, H0 is rejected.

Significance test/decision
Test performed in order to decide whether the null hypothesis should be retained or rejected.

Simple effect
Occurs where one level of one factor has a significant effect across levels of another factor.

Simulation
Study in which participants re-create and play through, to some extent, a social interaction.

Single blind
Procedure in an experiment where either participants or data assessors do not know which treatment each participant received.

Skew/skewed distributions
Non-normal distributions that have a lot more scores on one side of the mode than on the other.

Social desirability
Tendency of research participants to want to ‘look good’ and provide socially acceptable answers.

Spearman-Brown correction
In split-half reliability testing, provides an estimate of the true split-half reliability value from the correlation between two test halves, recognising that the raw split-half correlation is based on a set of items only half the length of the actual scale.

Spearman’s rho
Non-parametric, ordinal level measure of correlation; Pearson correlation on ranks of the paired raw scores.

Sphericity
Condition where there is homogeneity of variance among treatment variables and the variances of their differences are also similar.

Standard deviation
Measure of dispersion – the square root of: the sum of all squared deviations divided by N or N – 1.

Standard error
Standard deviation of a sampling distribution.

Standard score
Number of standard deviations a particular score is from its sample mean.

Standardisation
Setting up of measurement norms for the populations for whom a psychometric test is intended.

Standardised procedure
Tightly controlled steps taken by an experimenter with each participant and used to avoid experimenter bias or expectancy effects.

Standardised regression coefficient
Full name for beta values in multiple regression.

Stem and leaf chart
Exploratory data analysis tool showing every value in a data set but organised into class intervals to give a histogram shape.

Structure
Dimension of design which is the extent to which questions and procedure are identical for everyone.

Sum of squares
Addition of the squares of deviations around a mean.

Survey
Relatively structured questioning of large sample.

T

T
See Wilcoxon test.

t
See related and unrelated t test.

Target population
Similar to sampling frame but more theoretical. The assumed population of people from which a sample is to be drawn. Very often the aim is to be able to generalise sample results to this population.

Test norms
Test statistics for known and identifiable groups who have taken the test. These can be used to make a fair comparison for individual test takers.

Thematic analysis (TA)
General analysis of qualitative data into super-ordinate and subordinate themes which are extracted from the data. Not allied to any epistemological position.

Theoretical sampling
Use of purposive sampling (see above) to find data that might support or contradict an emergent explanatory framework.

Ties (tied ranks)
Feature of data when scores are given identical rank values.

Time-lag study
Comparative study where measures are repeated at long intervals on an equivalent sample each time (say, new sample of 5 year olds each year).

Time sampling

Time series
Line chart showing measures of a variable at progressive time intervals.

Time-series design
Design in which behaviour is recorded for a certain period before and after a treatment point in order to look for relatively sudden change.

Total variance
Variance of all scores in a set around their grand mean.

Transcription
Written recording of directly recorded speech as exactly as possible; often includes pauses, intonation, etc.

Transformation of data
Performed in order to remove skew from a data set so that it conforms to a normal distribution thus enabling the use of parametric tests.

Triangulation
Comparison of at least two views/explanations of the same thing(s) – events, behaviour, actions, etc.

Trimmed mean
The mean of a data set with its most extreme 5% of values removed.

True experiment
Experiment in which the experimenter has complete control over the manipulation of the independent variable and control of all other relevant variables, including random allocation to conditions.

Tukeya (HSD) post hoc
Post hoc test of all possible pairwise comparisons; appropriate analysis choice with a large number of means; considered conservative.

Tukeyb post hoc analysis
Less conservative post hoc test than Tukeya.

Two-tailed test
Test referring to both tails of the probability distribution under H0; must be used if alternative hypothesis is non-directional.

Type I error
Mistake made in rejecting the null hypothesis when it is true.

Type II error
Mistake made in retaining the null hypothesis when it is false.

U

U
See Mann-Whitney test.

Unbiased estimate (of SD)
Version of standard deviation or variance that is used for population estimates (uses N – 1 as denominator).

Uncorrected (SD)
Version of standard deviation or variance that is used if only wanting summary statistics for the group and not making population estimates (uses N as denominator).

Unrelated t test
Parametric difference test for unrelated data at interval level or above.

Upper hinge
On a box-plot, the third quartile.

V

Validity
The extent to which an effect demonstrated in research is genuine, not produced by spurious variables and not limited to a specific context. Extent to which a test measures the construct that it was intended to measure. Extent to which instruments measure what they were intended to measure. Also, extent to which a research effect can be trusted as real or as not ‘contaminated’ or confounded.

Concurrent
Extent to which test results conform with those on another test assumed to measure the same construct and taken at the same time.

Construct
Extent to which conceptions and operational measures of variables encompass the intended theoretical constructs. The constructs can be of persons (samples), treatments (IVs), observations (DV measures) and settings. Extent to which the existence of a construct is established through an interlinked set of diverse research findings. The theoretical establishment of a psychological construct through concerted and logically related psychological research.

Content
Extent to which test covers the whole of the relevant topic area, as assessed by experts.

Criterion
Extent to which test scores can predict phenomena such as difference between groups.

Internal
Extent to which an effect found in a study can be taken to be genuinely caused by manipulation of the independent variable.

Ecological
Widely overused term which can generally be replaced with ‘representative design’. Also used to refer to extent a research effect generalises across situations. The original meaning comes from cognitive psychology and refers to the degree to which a proximal stimulus predicts the distal stimulus for the observer. Should not be automatically applied to the laboratory/field distinction.

External
Extent to which results of research can be generalised across people, places and times.

Face
Extent to which the validity of a test is self-evident.

Known groups
Test of criterion validity involving groups between whom scores on the test should differ.

Population
Extent to which research effect can be generalised across people.

Predictive
Extent to which test scores can be used to make a specific prediction on some other variable.

Threat to
Any aspect of the design or method of a study that weakens the likelihood that a real effect has been demonstrated or that might obscure the existence of a real effect.

Variable
Quantity that can change; usually used to refer to a measure of phenomena.

Variance estimate
Estimate of variance in a variable accounted for by the correlation of another variable (or other variables) with it.

Variance ratio test
Full name for the test producing the F statistic – see above.

Variance
Measure of dispersion – square of standard deviation.

Variation ratio
Measure of dispersion – proportion of non-modal values to all values.

Verbal protocol
Recording of participant’s speech when they have been asked to talk or think aloud during a task.

Vignette
A story, scenario or other description given to all participants but with certain details altered and this difference constitutes the independent variable.

X

Y