Research Article
A New Method for Imputing Censored Values in Crossover Designs with Time-to-Event Outcomes Using Median Residual Life
Table 4
Event times (min) for a 10 min treadmill test in a
crossover clinical trial.
| Placebo-drug sequence | Drug-placebo sequence | | Period 1 (placebo) | Period 2 (drug) | | Period 1 (drug) | Period 2 (placebo) | Subject (age) | X1 | Y1 | X2 | Y2 | Subject (age) | X1 | Y1 | X2 | Y2 |
| 1 (52.91) | 1.5 | 1 | 1 | 1.5 | 2 (65) | 1 | 1 | 1 | 2.5 | 3 (45.79) | 6 | 4 | 3.5 | >10 | 4 (40) | 6 | >10 | 2.5 | 2.5 | 5 (64.37) | 1 | 1 | 1.5 | 4.5 | 6 (59.08) | 3 | 2 | 1 | .5 | 7 (54.13) | 3.5 | 1.5 | .5 | 3 | 8 (63.46) | 2.5 | 2.5 | 1.5 | 2 | 9 (61.14) | .5 | 1 | 3.5 | 8 | 10 (51.78) | 2 | 2.5 | 2.5 | 3 | 11 (47.59) | 6 | 10 | 6 | >10 | 12 (58.59) | 1.5 | 4.5 | 2.5 | 1 | 13 (70) | .5 | .5 | 1 | >10 | 14 (55.08) | 3.5 | 5.5 | 4.5 | 9.5 | 15 (57.28) | 1 | 1 | 1 | 2.5 | 16 (65.16) | 1 | 2 | 2 | >10 | 17 (59.75) | 1.5 | 1 | .5 | .5 | 18 (41.34) | 6 | >10 | 5 | 3.5 | 19 (67.77) | 1 | 1.5 | 2 | 4 | 20 (59.44) | 2 | 3 | 1.5 | 1.5 | 21 (42.91) | 5 | 5.5 | 3 | 1.5 | 22 (65.54) | 1.5 | 2.5 | 1.5 | .5 | 23 (50.72) | 2.5 | 5 | 6 | 4.5 | 24 (70) | 1.5 | 3.5 | 2.5 | 3 | 25 (47.01) | 5 | 5.5 | 4.5 | 6 | 26 (55.63) | 3.5 | 9 | 6 | 6 | 27 (62.26) | 1 | 2 | 2.5 | 8.5 | 28 (62.93) | 2 | 5.5 | 3.5 | 8 | 29 (40) | 5 | 5.5 | 3.5 | 2 | 30 (56.67) | 2.5 | 2.5 | 1 | .5 | 31 (66.27) | .5 | 1 | 2 | 7.5 | 32 (63.13) | 2.5 | 3.5 | 2.5 | 4 | 33 (48.16) | 5 | 4 | 2 | 2 | 34 (41.62) | 5.5 | 3 | 1 | .5 | 35 (65.04) | .5 | .5 | 1 | 1.5 | 36 (55.70) | 3 | 5.5 | 5 | .5 | 37 (66.49) | 1.5 | 2 | 3 | 3 | 38 (66.62) | .5 | 1 | 1 | 5.4 | 39 (43.19) | 6 | 4 | 1.5 | .5 | 40 (53.10) | 2.5 | 5 | 2.5 | .5 | Median | 1.5 | 1.75 | 2 | 3.5 | Median | 2.5 | 3.25 | 2.5 | 2.5 |
|
|
X1: baseline response in period 1; Y1: posttreatment response in period 1; X2: baseline response in period 2; Y2: posttreatment response in period 2.
|