Psychological Testing Study Notes

INTRODUCTION TO PSYCHOLOGICAL TESTING

Psychometrics

  • Definition by Galton (1879): Originally defined as the art of imposing measurement and number upon operations of the mind.
  • Contemporary Definition by The Psychometric Society: "A scientific discipline concerned with the construction of assessment tools, measurement instruments, and formalized models that connect observable phenomena (e.g., responses to items in an IQ test) to theoretical attributes (e.g., intelligence, personality)."
  • Application: Widely used in educational assessments to measure abilities in reading, writing, and mathematics.

Origins and Background of Psychometrics

  • Links to Psychophysics: Viewed as an outgrowth of earlier psychophysics, which studies the relationship between physical stimuli and psychological phenomena.
  • Key Historical Figures:
    • Fechner: Recognized as the Father of Psychometrics.
    • Alfred Binet: Developed the first psychometric instrument, the Stanford-Binet IQ test.
    • Charles Spearman: Pioneer in psychometrics, known for measuring intelligence; studied under Wilhelm Wundt.

Applications of Psychometric Theory

  • Measurement of:
    • Intelligence
    • Personality
    • Attitudes and beliefs
    • Academic achievement
    • Health-related fields
  • Challenges: The measurement of unobservable psychological constructs is complex and has led to definitions and quantification efforts.
  • Focus Areas: While intelligence has been extensively studied, a significant amount of focus is also on personality testing, e.g., Minnesota Multiphasic Personality Inventory (MMPI) and Myers-Briggs Type Indicator (MBTI).
  • Measurement Techniques: Often use Likert scales for measuring attitudes.

Theoretical Approaches in Psychometrics

1. Classical Test Theory (CTT)
  • Characteristics:
    • Dominant theory due to its simplicity and lower skill requirements for analysis.
    • Limits: Cannot analyze performance across different student groups or over time without identical assessment instruments.
    • Scores range strictly between 0% to 100%, making generalizations about underlying abilities (e.g., reading skills) impossible.
2. Item Response Theory (IRT)
  • Characteristics:
    • Gaining dominance due to explicit definitions of latent traits and effectiveness in measuring them.
    • Family of mathematical models explaining relationships between latent traits (e.g., reading ability) and test performances.
    • Establishes links between test items and the traits being measured, focusing on assessing an individual's position on an unobservable continuum.
  • Application Process Includes:
    • Adapting measurement tools for different contexts, field testing, data collection standardization, and generalizing results to target populations.

Scale vs Test

  • Scale: Collection of items measuring the same trait (e.g., a scale measuring Extraversion).
  • Test: Collection of one or more scales (e.g., a personality test measuring different personality traits).

Speed Tests vs Power Tests

Speed Tests
  • Characteristics: Timed tests assessing ability to respond quickly, with items of uniform difficulty.
  • Focus: Speed-oriented performance rather than mastery of content.
Power Tests
  • Characteristics: Untimed tests that allow for a full demonstration of skill or ability. Items increase in difficulty.
  • Objective: Determine depth of understanding and ability rather than speed of response.

Norm-Referenced vs Criterion-Referenced Tests

Norm-Referenced Tests
  • Purpose: Compare individual achievement against a normative group, distinguishing high and low achievers.
    • Focus: Broad measures and knowledge of academic content.
Criterion-Referenced Tests
  • Purpose: Assess how well a test taker has learned a specific body of knowledge or skills according to established criteria.
  • Characteristics: More beneficial for understanding an individual's skill mastery rather than comparison with peers.

Psychological Testing Defined

  • Definition: Psychological testing is defined as the process of administering, scoring, and interpreting psychological tests (Maloney & Ward, 1976).
  • Characteristics:
    1. Good tests sample representative behaviors.
    2. Standardized administration conditions.
    3. Scoring rules for objectivity.

Underlying Assumptions of Psychological Tests

  • Psychological tests measure what they purport to measure.
  • Test scores reflect unchanged behavior over time.
  • Comprehension, accurate self-report, truthfulness, and error levels in scoring are assumed.