Skip to main content
. Author manuscript; available in PMC: 2018 Dec 1.
Published in final edited form as: Psychol Methods. 2017 Dec;22(4):687–704. doi: 10.1037/met0000112

Table 2.

Power of Detecting the Significant Residual Covariances and the Average of Type I Error Rates of Falsely Detecting the Nonsignificant Residual Covariances

Loading Factor Corr. Residual Corr. Power1 Power2 Ave.Type I
1. 0.5 0.3 0.3 0.99 0.90 1.76%
2. 0.5 0.3 0.7 1.00 1.00 3.27%
3. 0.5 0.7 0.3 1.00 0.91 2.08%
4. 0.5 0.7 0.7 1.00 1.00 7.88%
5. 0.8 0.3 0.3 0.74 0.47 1.00%
6. 0.8 0.3 0.7 1.00 1.00 1.29%
7. 0.8 0.7 0.3 0.76 0.56 0.00%
8. 0.8 0.7 0.7 1.00 1.00 1.00%
9. 0.5 0.3 0.0 - - 1.53%
10. 0.5 0.7 0.0 - - 2.12%
11. 0.8 0.3 0.0 - - 1.00%
12. 0.8 0.7 0.0 - - 1.00%

13. 0.3 0.3 0.2 0.86 0.78 1.91%
14. 0.3 0.7 0.2 0.95 0.91 5.19%
15. 0.5 0.3 0.2 0.77 0.49 1.73%
16. 0.5 0.7 0.2 0.87 0.52 1.78%
17. 0.8 0.3 0.2 0.22 0.15 1.00%
18. 0.8 0.7 0.2 0.21 0.19 1.00%
19. 0.3 0.3 0.7 1.00 1.00 3.12%
20. 0.3 0.7 0.7 1.00 1.00 7.75%

Note:

Power1: The power of detecting the significance of ψ16.

Power2: The power of detecting the significance of ψ27.

Ave.Type I: The average of Type I error rates for falsely detecting the nonsignificant residual covariances.