Chapter 8 – Psychological Tests and Measurement Scales

Vocabulary flashcards covering major terms and definitions from Chapter 8 on psychological tests and measurement scales.

Psychometrics

Field concerned with the design, administration, scoring and evaluation of psychological tests and scales.

Psychological Test

Any structured procedure that attempts to quantify a psychological construct such as ability, personality or attitude.

Measurement Scale

Set of items or questions whose summed or averaged scores represent standing on a psychological construct.

Attitude Scale

Questionnaire designed to measure a relatively enduring evaluation of an issue, person or object.

Thurstone Scale

Attitude scale in which judges rate item favourability; each agreed‐with item gives the respondent its mean ‘scale value’.

Likert Scale

Summated ratings scale where respondents indicate strength of agreement (e.g., 1–5) on multiple items whose scores are totaled.

Semantic Differential

Scale that measures connotative meaning by having respondents rate a concept between bipolar adjectives (e.g., ‘honest ⟷ dishonest’).

Visual Analogue Scale (VAS)

Continuous line between two extremes on which the respondent marks a point; distance from one end becomes the score.

Diagnostic Item

Scale statement not overtly tied to the construct yet correlating strongly with overall scores, thus aiding discrimination.

Response (Acquiescence) Set

Tendency for some respondents to habitually agree (or disagree) with items regardless of content.

Social Desirability

Bias produced when people answer to look socially acceptable rather than reveal true attitudes or traits.

Disguise (in questioning)

Strategy of masking a test’s purpose so respondents cannot tailor answers to researcher expectations.

Bogus Pipeline Technique

Method using a sham lie detector to encourage truthful responses by making deception seem detectable.

Projective Test

Assessment that infers unconscious motives from interpretations of ambiguous stimuli (e.g., Rorschach).

Rorschach Ink-Blot Test

Projective test using symmetrical ink blots; responses are coded for themes presumed to reveal personality dynamics.

Thematic Apperception Test (TAT)

Projective measure in which stories told about ambiguous pictures are analyzed for underlying motives and conflicts.

Factor Analysis

Statistical technique that groups correlated items, providing evidence for underlying constructs measured by a test.

Reliability

Overall consistency of a test’s scores; high reliability means similar results under consistent conditions.

External Reliability

Stability of scores across repeated administrations of the same test (test–retest consistency).

Internal Reliability

Degree to which items on a scale are mutually consistent in measuring the same construct.

Split-Half Reliability

Correlation between scores on two equivalent halves of the same test, often corrected by Spearman-Brown formula.

Cronbach’s Alpha (α)

Index of internal consistency based on average inter-item correlations; values ≥ .75 usually indicate good reliability.

Kuder–Richardson Measure

Special form of Cronbach’s alpha for tests whose items are scored dichotomously (e.g., right/wrong, yes/no).

Test–Retest Reliability

Correlation of scores obtained by the same people on two separate occasions, indicating temporal stability.

Spearman-Brown Correction

Formula that estimates true split-half reliability for the full test length from the correlation between halves.

Item Analysis

Process of evaluating each item’s contribution to overall reliability, often by examining ‘alpha if item deleted’.

Item-Total Correlation

Correlation between scores on one item and total test score; low values suggest the item may not fit the scale.

Item Discrimination

Extent to which an item differentiates high from low scorers on the overall test.

Reliability Coefficient

Numerical estimate (e.g., α, r) indicating the reliability level of a scale.

Validity

Extent to which a test measures what it purports to measure.

Face Validity

Degree to which the purpose of a test appears obvious to users and examinees.

Content Validity

Expert-judged adequacy with which test items sample the entire domain of the construct or skill area.

Criterion Validity

Degree to which test scores relate to an external criterion; includes concurrent and predictive forms.

Concurrent Validity

Correlation between new test scores and established measure of the same trait obtained at the same time.

Predictive Validity

Ability of test scores to forecast future behaviour, performance or status on a relevant criterion.

Construct Validity

Broad confirmation of a test’s theoretical construct through converging evidence from diverse studies.

Standardisation

Process of developing population norms and uniform administration procedures for a psychological test.

Test Norms

Statistical summary (means, SDs, percentiles) of scores from a defined population used for comparative interpretation.

Psychometrist / Psychometrician

Specialist trained to create, evaluate and administer psychological tests and interpret their results.

Equal Appearing Intervals

Thurstone scaling method that assumes statements can be arrayed at equal attitudinal distances as judged by experts.

Visual Analogue Scale Scoring

Measurement of respondent’s mark distance (often in mm) from the low anchor to quantify subjective intensity.

Known-Groups Criterion

Validity strategy comparing test scores of groups already known to differ on the construct (e.g., anxious patients vs controls).