First Use of Multiple Imputation with the National Tuberculosis Surveillance System

Table 3

Errors in coefficient estimates for increasing numbers of imputed datasets.

	Number of imputed datasets
	2	3	4	5	6	7	8	9	10
Coefficient for isoniazid resistance	0.71	0.72	0.72	0.73	0.72	0.73	0.73	0.74	0.74
Within-imputation error	0.23	0.23	0.23	0.23	0.23	0.23	0.23	0.23	0.23
Between-imputation error	0.11	0.08	0.07	0.06	0.05	0.05	0.05	0.05	0.05
Coefficient for HIV infection	1.44	1.33	1.29	1.27	1.25	1.24	1.23	1.24	1.23
Within-imputation error	0.14	0.14	0.14	0.14	0.14	0.14	0.14	0.14	0.14
Between-imputation error	0.31	0.28	0.24	0.22	0.20	0.19	0.17	0.16	0.16