Psychological Assessments and Test Reliability

Flashcards on psychological assessments, score normalization, test reliability based on lecture notes.

What is a psychological assessment?

A procedure for quantifying behaviour, attitudes, and feelings to make an inference about a psychological construct.

What is a construct in psychological assessment?

A mental attribute that is not directly observable, but is inferred from observed behaviors.

What is a psychological assessment?

A procedure for quantifying behaviour, attitudes, and feelings to make an inference about a psychological construct.

What is a construct in psychological assessment?

A mental attribute that is not directly observable, but is inferred from observed behaviors.

Why are psychological assessments objective?

To avoid subjective personal judgment/intuition by eliminating individual bias and using standardized stimuli and methods.

What are some uses of psychological assessments?

Suitability for employment, clinical diagnosis, safety protocols, and scientific hypothesis testing.

What is a raw score?

The score of an individual on a test, which is not meaningful without a standard for comparison.

What is a derived score?

A score calculated by transforming the raw score to allow comparison to a normative sample.

What are examples of derived scores?

Percentile ranks and z-scores.

What is a percentile score?

Percentage of people in the sample who fall below a particular raw score.

What is the formula for calculating percentile (P)?

(n/N) x 100, where n is the number of data points below the data point of interest and N is the total number of values in the data set.

What are advantages of using percentiles?

Easy to compute, readily understood, and universally applicable.

What are disadvantages of using percentiles?

Inequality of units (scaling).

What is a z-score?

A measure of how extreme your data point is relative to a normative sample, shown in standard deviations from the mean.

How do you calculate a z-score?

(X - M) / Sd, where X is the raw score, M is the mean of all scores, and Sd is the standard deviation of all scores.

What are measures based on z-scores?

T-Score, Sten score, Deviation IQ, and Stanine.

What is specificity of norms?

Specific to the population from which they are derived.

What does a good test provide?

Consistency in administration, scoring, and interpretation.

What is reliability?

Reproducibility or consistency of measurements.

What is validity?

Extent to which a test measures what it's intended to measure.

What is Pearson's Product Moment Correlation Coefficient?

The strength and direction of the linear relationship between two variables, ranging between -1 and +1.

Who developed the Classical Test Theory (True Score Theory)?

Spearman (1904).

What does the mean of the distribution of scores reflect?

The mean of the distribution of scores.

What is the standard error of measurement?

The standard deviation of the distribution of scores.

How can you express the observed score?

Xi = ti + ei, where Xi is the observed score, ti is the true score, and ei is the random measurement error.

How can you express the observed score variance?

S2x = s2t + s2e, where S2x is the observed score variance, s2t is the true score variance, and s2e is the error variance.

What is the error variance attributable to in test-retest reliability?

Changes in testing conditions and test-takers between the two occasions.

What is the error variance attributable to in alternate forms reliability?

Content sampling (differences in item content) and time sampling when the 2nd test is delayed.

What is the error variance due to in split-half reliability?

Content sampling.

What is the error variance attributed to in Cronbach's Alpha & Kuder-Richardson reliability?

Content sampling and heterogeneity of the behavior domain sampled.

What is the error variance due to in inter-rater reliability?

Difference between raters.