Psychological Testing & Assessment – Core Vocabulary

Vocabulary flashcards summarizing essential psychometric, statistical, and ethical terms drawn from the lecture notes to aid RPm exam preparation.

Psychological Testing

Process of measuring psychology-related variables with standardized devices or procedures to obtain numerical samples of behavior.

Psychological Assessment

Gathering and integrating psychology-related data to answer a referral question through multiple evaluation tools.

Ability (Maximal Performance) Test

Assessment designed to determine what a person can do under optimal conditions.

Achievement Test

Exam that measures previous learning or mastery of specific subject matter.

Aptitude Test

Instrument that estimates the potential for learning or acquiring specific skills; emphasizes predictive validity.

Intelligence Test

Measure of general potential for problem solving, adaptation, abstract thought, and learning from experience.

Typical Performance Test

Assessment of usual or habitual thoughts, feelings, and behaviors with no right or wrong answers.

Personality Test

Tool that measures enduring dispositions and preferences, either ideographically or nomothetically.

Structured Personality Test

Self-report inventory providing fixed responses (e.g., true/false) to statements about typical behavior.

Projective Personality Test

Unstructured measure using ambiguous stimuli to elicit projection of inner dynamics.

Speed Test

Assessment in which performance is gauged by the number of correct responses within a strict time limit.

Power Test

Exam emphasizing item difficulty; ample time is provided so speed plays little role.

Cut Score

Reference point, set by judgment, that divides test scores into categories (e.g., pass/fail).

Psychometric Soundness

Overall technical quality of a measurement instrument, encompassing reliability and validity.

Reliability

Consistency or dependability of test scores across administrations, items, or raters.

Validity

Degree to which evidence and theory support the interpretations of test scores for intended uses.

Trait

Relatively enduring characteristic that differentiates one individual from another.

State

Temporary condition reflecting how someone feels or behaves at a specific moment.

Construct

Scientific concept inferred from behavior and used to explain psychological phenomena.

Classical Test Theory (CTT)

Model asserting that an observed score equals a true score plus random measurement error.

Error Variance

Portion of score variance attributable to factors other than the trait being measured.

Standard Error of Measurement (SEM)

Index reflecting the expected error in an individual observed score; inversely related to reliability.

Test–Retest Reliability

Correlation of scores from the same test administered to the same group on two occasions.

Parallel-Forms Reliability

Correlation between scores on two equivalent versions of a test given to the same group.

Split-Half Reliability

Internal consistency estimate obtained by correlating two halves of a single test administration.

Cronbach’s Alpha

Coefficient estimating internal consistency for scales with items scored in multiple categories.

KR-20

Reliability formula for dichotomously scored items with unequal item variances.

Inter-Scorer Reliability

Degree of agreement among different raters scoring the same performance.

Face Validity

Extent to which a test appears, on the surface, to measure the intended construct.

Content Validity

Judgment of how well test items represent the domain of interest.

Construct Validity

Evidence that test scores relate to other measures as predicted by theory of the underlying construct.

Criterion Validity

How well test scores predict or correlate with an external criterion (concurrent or predictive).

Convergent Evidence

High correlations between the test and other measures of the same construct.

Discriminant Evidence

Low correlations between the test and measures of unrelated constructs.

Incremental Validity

Amount of additional predictive value a new test provides beyond existing measures.

Multitrait-Multimethod Matrix

Table of correlations used to examine convergent and discriminant validity across traits and methods.

Factor Analysis

Statistical technique identifying latent variables that account for interrelationships among test items.

Standard Score

Converted score expressed relative to a distribution’s mean and standard deviation (e.g., z, T, stanine).

Z-Score

Standard score with mean 0 and SD 1 indicating how many SDs a raw score lies from the mean.

T-Score

Standard score with mean 50 and SD 10 eliminating negative values.

Stanine

Nine-point standard score scale with mean 5 and SD 2.

Norm-Referenced Test

Assessment interpreted by comparing an individual’s score to scores of a norm group.

Criterion-Referenced Test

Test interpreted by comparing performance to a defined level of proficiency, not to other people.

Base Rate

Proportion of the population that actually possesses the characteristic being predicted.

Sensitivity (True Positive Rate)

Ability of a test to correctly identify individuals who have the condition of interest.

Specificity (True Negative Rate)

Ability of a test to correctly identify individuals who do not have the condition of interest.

False Positive

Case where test predicts success or presence but outcome is failure or absence.

False Negative

Case where test predicts failure or absence but outcome is success or presence.

Utility

Practical value of a test in improving decision-making efficiency, often evaluated via cost–benefit analysis.

Taylor-Russell Tables

Tables estimating improvement in selection accuracy when a test is added to a decision process.

Item Difficulty Index (p)

Proportion of examinees who answer an item correctly; higher values indicate easier items.

Item Discrimination Index (D)

Statistic reflecting how well an item differentiates high scorers from low scorers on the total test.

Item Characteristic Curve (ICC)

Graph in IRT showing probability of a correct response across levels of ability.

Guessing Parameter

IRT value estimating likelihood of low-ability examinees answering an item correctly by chance.

Computerized Adaptive Testing (CAT)

Interactive testing method in which subsequent items are selected based on a test taker’s previous responses.

Pilot Study

Preliminary research conducted to refine items and administration procedures before full test development.

Item Pool

Large reservoir of potential items created during test construction.

Test Blueprint (Table of Specifications)

Plan outlining content areas and cognitive levels to ensure representative item sampling.

Ipsative Scoring

Comparing an individual’s scores on different scales within the same test to each other.

Cumulative Scoring Model

Approach where higher total of keyed responses indicates higher standing on the trait.

Empirical Criterion Keying

Selecting items based on their ability to discriminate between groups defined by an external criterion.

Differential Item Functioning (DIF)

Condition where individuals from different groups but equal ability have differing probabilities of endorsing an item.

Flynn Effect

Observed generational rise in average intelligence test scores over time.

Culture Fair Test

Instrument designed to minimize cultural content and reduce bias across groups.

Culture Loading

Extent to which a test is saturated with language, knowledge, or values specific to a culture.

Back-Translation

Process of translating a test into another language and then back to the original to check equivalence.

Standard Error of Estimate

Standard deviation of residuals in regression, indicating accuracy of predicted criterion scores.

Hit Rate

Proportion of correct decisions (true positives + true negatives) made using the test.

Groupthink

Decision-making bias where desire for consensus overrides appraisal of alternative courses.

Halo Effect

Rating error in which a rater’s overall impression influences specific ratings.

Central Tendency Error

Rater bias of clustering evaluations around the middle category of a scale.

Leniency Error

Systematic rater tendency to give overly favorable evaluations.

Severity Error

Systematic rater tendency to give overly harsh evaluations.

Barnum Effect

People’s tendency to accept vague, general personality descriptions as uniquely applicable to themselves.

Reactance (Hawthorne Effect)

Change in behavior that occurs because individuals know they are being observed or evaluated.

True Score

Hypothetical average score a person would obtain over infinite administrations free from error.

Standard Error of the Difference

Index used to judge whether the difference between two test scores is statistically significant.

Confidence Interval

Range of scores around an observed score likely to contain the true score at a given probability level.

Restriction of Range

Condition where limited variability in scores lowers observed correlations.

Skewness

Degree of asymmetry in a distribution; positive skew has a long right tail, negative skew a long left tail.

Kurtosis

Measure of peakedness or flatness of a distribution relative to normal.

Mean

Arithmetic average; point of least squares in a distribution.

Median

Middle score that divides a distribution into two equal halves; resistant to outliers.

Mode

Most frequently occurring score in a distribution.

Variance

Average squared deviation of scores from the mean; basis for standard deviation.

Interquartile Range

Difference between the first and third quartiles; middle 50% spread.

Pearson r

Correlation coefficient for linear relationship between two continuous variables.

Spearman Rho

Rank-order correlation coefficient for ordinal data or non-linear monotonic relationships.

Point-Biserial Correlation

Correlation between a continuous variable and a true dichotomy.

Phi Coefficient

Correlation between two true dichotomous variables.

Independent t-Test

Statistical test comparing means of two independent groups.

Paired t-Test

Test comparing means of two related scores from the same group.

One-Way ANOVA

Analysis testing mean differences among three or more groups on one independent variable.

ANCOVA

ANOVA that statistically controls for effects of a covariate continuous variable.

Chi-Square Test of Independence

Non-parametric test assessing association between two categorical variables.

Kolmogorov-Smirnov Test

Test for normality used with sample sizes greater than 50.

Levene’s Test

Procedure for testing equality of variances across groups.

Item Response Theory (IRT)

Measurement model relating probability of a response to latent trait level and item parameters.

Latent Trait

Unobserved characteristic quantified in IRT models.

Discrimination Parameter

IRT indicator of how well an item differentiates among examinees with different ability levels.