- Manual
- Chapter 1: Introduction
- Chapter 2: Administration
- Chapter 3: Scoring and Reports
- Chapter 4: Interpretation
- Chapter 5: Case Studies
- Chapter 6: Development
- Chapter 7: Standardization
- Chapter 8: Reliability
- Chapter 9: Validity
- Chapter 10: Fairness
- Chapter 11: Conners 4–Short
- Chapter 12: Conners 4–ADHD Index
- Appendices
Key Findings |
Results presented in this chapter provide strong evidence that the Conners 4 meets or exceeds the fairness requirements outlined in the Standards for Educational and Psychological Testing (AERA, APA, & NCME, 2014).
Gender. Results provide evidence for the equivalent measurement of males and females and support the absence of meaningful gender differences on the Conners 4. Main results include the following:
- No evidence of measurement invariance was found (the factor structure, loadings, thresholds, and intercepts are invariant between males and females).
- No evidence of differential test functioning was found (trivial effect sizes observed: median ETSSD = |0.02|).
- In comparing mean scores between males and females, no meaningful gender differences were found on the Parent or Self-Report forms. Teachers tended to rate male students higher than female students, with negligible to small effect sizes (Cohen’s d = |0.04 to 0.40|).
Race/Ethnicity. Results demonstrate an absence of measurement bias for the Conners 4 scales by different races/ethnicities, supporting its appropriate use in racially and ethnically diverse populations. These results include the following:
- No evidence of measurement invariance was found between the tested groups.
- No evidence of differential test functioning was found (trivial effect sizes observed: median ETSSD = |0.02|).
- In comparing mean scores between groups, different patterns were found for the different comparisons.
- For White vs. Hispanic and White vs. Asian comparisons, no meaningful race/ethnicity differences were found across raters.
- For White vs. Black comparisons, no meaningful differences were found for Parent and Self-Report forms. The effect of student race on the Teacher form was statistically significant for several scales, wherein ratings of Black students resulted in slightly higher scores than ratings of White students (Cohen’s d ranging from 0.00 to |0.43|), yielding a T-score difference of up to 4 points. This trend of ratings may be important to keep in mind when interpreting a teacher’s ratings or when comparing results for Black youth from the Parent and Self-Report form to the Teacher form, as one may erroneously conclude that the youth behaves differently in different settings.
Country of Residence. Results reveal no evidence of measurement bias in terms of country of residence, when comparing youth in the U.S. and Canada on the Conners 4. Key results include the following:
- No evidence of measurement invariance was found (the factor structure, loadings, thresholds, and intercepts are invariant between U.S. and Canada).
- No evidence of differential test functioning was found (negligible effect sizes observed: median ETSSD = |0.06|).
- In comparing mean scores between countries, no statistically significant differences were found across raters, and effect sizes were negligible to small (Cohen’s d = 0.00 to |0.31|).
Parental Education Level (PEL). Results provide evidence for equivalence between youth with different levels of parental education on the Conners 4. These results include the following:
- No evidence of measurement invariance was found (the factor structure, loadings, thresholds, and intercepts are invariant between youth with low PEL and high PEL).
- No evidence of differential test functioning was found (negligible effect sizes observed: median ETSSD = |0.08|).
- In comparing mean scores between the levels of a parent’s educational attainment, negligible to small effects were observed (Cohen’s d = 0.00 to |0.31|).
| << Overview | Methods of Evaluating Measurement Bias >> |