Mathematical Problems in Engineering / 2014 / Article / Tab 2 / Research Article
A Two-Sample Parametric Test for Partly Interva-Censored Data with Nonproportional Hazard Table 2 Estimated power and size of a test with
exact observation based on simulated data with 10 multiple imputations and 1000 replications at the significance level 0.05 (0.01).
Early difference Power ST 0.335 0.314 0.289 0.728 0.697 0.669 0.960 0.946 0.933 (0.157) (0.142) (0.119) (0.486) (0.448) (0.401) (0.886) (0.864) (0.811) Power LRT 0.236 0.239 0.231 0.626 0.607 0.595 0.890 0.885 0.854 (0.083) (0.094) (0.093) (0.390) (0.392) (0.367) (0.824) (0.819) (0.778) Size ST 0.037 0.036 0.040 0.029 0.033 0.039 0.035 0.044 0.046 (0.008) (0.007) (0.012) (0.007) (0.005) (0.005) (0.002) (0.004) (0.002) Size LRT 0.034 0.041 0.053 0.033 0.038 0.051 0.041 0.059 0.064 (0.007) (0.007) (0.013) (0.007) (0.008) (0.006) (0.002) (0.005) (0.008) Late difference Power ST 0.211 0.222 0.227 0.494 0.477 0.460 0.835 0.826 0.810 (0.056) (0.064) (0.061) (0.213) (0.201) (0.194) (0.600) (0.585) (0.558) Power LRT 0.236 0.252 0.255 0.516 0.514 0.517 0.854 0.847 0.839 (0.074) (0.085) (0.095) (0.250) (0.259) (0.251) (0.631) (0.634) (0.621) Size ST 0.027 0.027 0.031 0.033 0.040 0.035 0.037 0.038 0.038 (0.004) (0.006) (0.006) (0.007) (0.008) (0.004) (0.005) (0.004) (0.008) Size LRT 0.033 0.034 0.050 0.041 0.048 0.053 0.041 0.042 0.048 (0.009) (0.007) (0.008) (0.010) (0.010) (0.008) (0.008) (0.008) (0.011) Cross difference Power ST 0.646 0.627 0.581 0.939 0.916 0.890 1 0.997 0.995 (0.428) (0.413) (0.357) (0.846) (0.812) (0.754) (0.989) (0.985) (0.970) Power LRT 0.484 0.516 0.508 0.912 0.915 0.907 0.999 0.999 0.998 (0.269) (0.285) (0.286) (0.830) (0.826) (0.806) (0.993) (0.991) (0.989) Size ST 0.052 0.056 0.054 0.039 0.045 0.056 0.038 0.036 0.044 (0.012) (0.013) (0.018) (0.008) (0.010) (0.012) (0.006) (0.006) (0.011) Size LRT 0.063 0.077 0.092 0.059 0.078 0.095 0.051 0.063 0.078 (0.011) (0.012) (0.023) (0.016) (0.020) (0.028) (0.007) (0.015) (0.023)
