Table VII.

Renal cancer data: results of proportional hazards models by complete cases and eight different imputation methods. Tabulated values are (standard error).

	CC	Imputation methods (n=347)
Variable	(n = 169)	NO-T	LOGT	T	T2	NA	COX	COX*
esr/35.1	0.30	0.10	0.24	0.21	0.11	0.26	0.25	0.25
	(0.11)	(0.10)	(0.12)	(0.12)	(0.12)	(0.12)	(0.12)	(0.11)
who2	−0.95	−0.84	−0.87	−0.86	−0.84	−0.87	−0.87	−0.87
	(0.24)	(0.17)	(0.17)	(0.17)	(0.17)	(0.18)	(0.17)	(0.17)
who3	−0.62	−0.62	−0.62	−0.61	−0.61	−0.61	−0.61	−0.61
	(0.22)	(0.14)	(0.15)	(0.15)	(0.15)	(0.15)	(0.15)	(0.15)
haem/2.00	−0.44	−0.33	−0.27	−0.28	−0.33	−0.26	−0.26	−0.26
	(0.12)	(0.09)	(0.10)	(0.10)	(0.10)	(0.10)	(0.10)	(0.10)
wcc^3/13.5	0.41	0.33	0.34	0.34	0.33	0.34	0.34	0.34
	(0.13)	(0.08)	(0.08)	(0.08)	(0.08)	(0.08)	(0.08)	(0.08)
log(t_mt+1)/1.42	−0.24	−0.23	−0.24	−0.24	−0.23	−0.24	−0.24	−0.24
	(0.09)	(0.06)	(0.06)	(0.06)	(0.06)	(0.06)	(0.06)	(0.06)
trt	−0.44	−0.37	−0.37	−0.37	−0.37	−0.37	−0.37	−0.37
	(0.16)	(0.12)	(0.12)	(0.12)	(0.12)	(0.12)	(0.12)	(0.12)

Bold cells indicate estimates that differ from the NA estimate by more than 20 per cent of the NA standard error, or standard errors that differ from the NA standard error by more than 20 per cent of the NA standard error. Monte Carlo error in parameter estimates is no more than 0.003 in all cases.