BMC Medical Research Methodology

Table 2 Linear regression with Y ~ N ((X-2)², ϕ)

From: Multiple imputation of missing covariates with non-linear effects and interactions: an evaluation of statistical methods

	R ²= 0.1			R ² = 0.5			R ² = 0.8
	bias	cover	r.prec.	bias	cover	r.prec.	bias	cover	r.prec.
	MCAR, X ~ normal
CData	-1	95	100	0	95	100	0	95	100
CCase	0	95	64	0	95	64	0	95	64
Passive	-31	86	110	-31	48	55	-30	32	21
PMM	-2	93	62	1	93	61	2	90	47
JAV	-1	94	64	0	93	63	0	92	52
	MAR, X ~ normal
CData	0	94	100	0	95	100	0	94	100
CCase	-14	92	54	-9	88	37	-4	91	30
Passive	-41	80	108	-38	45	52	-32	48	18
PMM	-10	88	42	4	88	26	16	51	10
JAV	0	93	41	18	68	21	22	19	10
	MAR, X ~ log normal
CData	2	94	100	0	95	100	0	95	100
CCase	-12	94	44	-8	94	27	-4	94	20
Passive	-41	96	81	-25	87	18	-9	90	4
PMM	-10	88	29	8	91	12	35	70	3
JAV	7	92	27	41	70	6	71	20	2

Table 2 Percentage bias, coverage and relative precision for quadratic term in linear regression when Y ~ N ((X-2)², ϕ). For MCAR, X ~ normal, the maximum MCSEs among the five methods are 1, 0 and 0% for R ² = 0.1, 0.5 and 0.8, respectively. For MAR, X ~ normal, they are 1, 1 and 1%. For MAR, X ~ log normal, they are 2, 2 and 2%

Back to article page

ISSN: 1471-2288

Contact us

General enquiries: journalsubmissions@springernature.com