THE ANALYSIS OF INCOMPLETE DATA IN THE 3-PERIOD 2-TREATMENT CROSS-OVER DESIGN FOR CLINICAL-TRIALS

The additional time to complete a three-period two-treatment (3P2T) cr oss-over trial may cause a greater number of patient dropouts than wit h a two-period trial. This paper develops maximum likelihood (ML), sin gle imputation and multiple imputation missing data analysis methods f or the 3P2T cross-over designs. We use a simulation study to compare a nd contrast these methods with one another and with the benchmark meth od of missing data analysis for cross-over trials, the complete case ( CC) method. Data patterns examined include those where the missingness differs between the drug types and depends on the unobserved data. De pending on the missing data mechanism and the rate of missingness of t he data, one can realize substantial improvements in information recov ery by using data from the partially completed patients. We recommend these approaches for the 3P2T cross-over designs.