Beyond Reliability and Validity:

Choosing the Best Measure for Your Study

I. Overview

II. Sensitivity: Will the measure be able to detect the differences you need to detect?

A. Achieving the necessary level of sensitivity

1. Look for high validity2. Look for high reliability

3. Allow scores to vary

4. Avoid behaviors that are resistant to change

5. Avoid measures that produce a limited range of scores

6. Ask how much instead of whether

7. Add scale points to a rating scale

8. Pilot test your measure

B. Sensitivity: Conclusions

III. Scales of Measurement: Will the measure allow you to make the kinds of comparisons you need to make?

A. The different scales of measurement

1. Nominal numbers: Different numbers representing different statesB. Why our numbers do not always measure up2. Ordinal numbers: When bigger means more

3. Interval scale numbers: Knowing how much more

4. Ratio scales: Zeroing in on perfection

C. Which level of measurement do you need?

1. When you need ratio scale dataD. Conclusions about scales of measurement2. When you need at least interval scale data

3. When ordinal data is sufficient

4. When you only need nominal scale data

IV. Ethical and practical considerations

V. Concluding remarks

Summary

Exercises

Back to Chapter 6 Menu