A New Method for Imputing Censored Values in Crossover Designs with Time-to-Event Outcomes Using Median Residual Life

Table 1

True values used in simulation study under the alternative hypothesis for each combination of distribution, mean pairwise correlation coefficient, percentage of censoring, and sample size.

Mean pairwise correlation
Percentage of censoring	30%			50%			30%			50%
	12	24	48	12	24	48	12	24	48	12	24	48
Dist
Exp	2.33	1.59	1.6	2.3	1.8	1.5	2.1	1.7	1.5	2	1.52	1.35
Weibull	2.3	1.93	1.68	2.3	1.69	1.51	2	1.78	1.56	2	1.64	1.28
Gamma	2.1	1.4	1.3	1.95	1.65	1.2	2	1.4	1.24	2.1	1.3	1.14