Table 9. Regression Including Both Sleep Problems and Testosterone: Both Predict Aggression in Men on Statins and Simvastatin (but Not Pravastatin or Placebo).

	Change in Testosterone			Baseline Testosterone			Change in Sleep Problems			Baseline Sleep Problems
	Beta ± SE	95% CI	P	Beta ± SE	95% CI	P	Beta ± SE	95% CI	P	Beta ± SE	95% CI	P
On Placebo N = 161	0.039 ± 0.20	-0.35, 0.43	0.85	-0.033 ± 0.22	-0.46, 0.39	0.88	0.079 ± 0.61	-1.1, 1.3	0.90	-0.15 ± 0.13	-0.40, 0.095	0.23
On Pravastatin N = 152	-0.076 ± 0.31	-0.69, 0.54	0.81	-0.24 ± 0.32	-0.88, 0.40	0.46	0.26 ± 0.74	-1.2, 1.7	0.72	0.13 ± 0.15	-0.17, 0.44	0.39
On Statins N = 316	0.62 ± 0.29	0.041, 1.2	0.036	0.78 ± 0.30	0.19, 1.4	0.010	2.5 ± 0.59	1.3, 3.6	<0.001	0.27 ± 0.15	-0.024, 0.56	0.072
On Simvastatin N = 164	1.2 ± 0.47	0.31, 2.2	0.009	1.3 ± 0.49	0.36, 2.3	0.007	3.5 ± 0.84	1.8, 5.2	<0.001	0.28 ± 0.25	-0.21, 0.76	0.26

Beta = regression coefficient; CI = confidence interval; SE = standard error. Findings were nonsignificant for either testosterone or sleep problems (baseline or change) on pravastatin (and on placebo), which did not increase sleep problems and did not significantly reduce testosterone in this study.