RM wk 4
- 2. Measurement Validity • Measures the construct it intends to measure. • Face Validity – Appearance • Criterion-Oriented Validity – Predictive validity – Convergent vs Discriminant Validity
- 3. Methodological Approaches • Quantitative approaches – Numerical – Observational results can be statistically analyzed. • Qualitative approaches – Non-numerical – Statistical analysis of data is not possible.
- 4. Systematic Observation • Careful observation of specific behaviors in specific settings using structured, quantifiable methods. – Coded numerically • Can be analyzed statistically. • Reactivity Problem – Demand characteristics
- 5. Naturalistic Observation • Descriptive format – Can be qualitative or quantitative • Observations are interpreted • Issues include participation, deception, and range of observation
- 6. Other forms • Case studies –Describes and unique situation that informs further research • Archival Research –Data previously collected • Can lead to question of accuracy
- 7. Measurement Scales • Nominal – Named categories • Ordinal – Orders categories from first to last • Interval – Numerical and equidistant, but arbitrary (no zero point) • Ratio – Numerical and equidistant, with a zero point
- 8. Measurement Reliability • Measurements consist of two inferred components. – True score – Measurement error • The higher the correlation (r near 1) between two measurements, the more reliable
- 9. Reliability • Reliability is analogous to consistency. • Both validity and reliability are needed in research. – A valid measure truly measures what it purports to measure. – A reliable measure produces the same result each time the measurement is taken.
- 10. Reliability • Test-Retest Reliability – 2x • Internal Consistency Reliability – Split-test – Item correlations • Cronbach’s α • Inter-rater Reliability – Correlating rater scores
- 11. Reliability
- 12. Using a Scatterplot To Evaluate Reliability
- 13. Internal Consistency & Test- Retest Reliability