Missing data and censoring in the analysis of progression-free survival in oncology clinical trials.

Progression-free survival (PFS) is increasingly used as a primary endpoint in oncology clinical trials. However, trial conduct is often such that PFS data on some patients may be partially missing either due to incomplete follow-up for progression, or due to data that may be collected but confounded by patients stopping randomized therapy or starting alternative therapy prior to progression. Regulatory guidance on how to handle these patients in the analysis and whether to censor these patients differs between agencies. We present results of a reanalysis of 28 Phase III trials from 12 companies or institutions performed by the Pharmaceutical Research and Manufacturers Association-sponsored PFS Expert Team. We show that analyses not adhering to the intention-to-treat principle tend to give hazard ratio estimates further from unity and describe several factors associated with this shift. We present illustrative simulations to support these findings and provide recommendations for the analysis of PFS.

The efficacy and safety of tadalafil: an update.

OBJECTIVE: To provide an update on the efficacy and safety of tadalafil, a phosphodiesterase-5 inhibitor, in the treatment of erectile dysfunction (ED). PATIENTS AND METHODS: In all, 2102 men (mean age 56 years) with mild-to-severe ED of various causes were randomized to placebo or tadalafil, taken as needed with no food restrictions, at fixed 'on-demand' doses of 10 or 20 mg in 11 randomized, double-blind, placebo-controlled trials lasting 12 weeks. The three co-primary outcomes were changes from baseline in the erectile function domain of the International Index of Erectile Function (IIEF) and the proportion of 'yes' responses to questions 2 and 3 of the Sexual Encounter Profile (SEP). Additional efficacy instruments included a Global Assessment Question (GAQ). RESULTS: Compared with placebo, tadalafil gave significantly better outcomes. Patients receiving either dose of tadalafil had a significant mean improvement of 6.5 and 8.6, respectively, in the IIEF erectile function domain score from baseline (P < 0.001 vs placebo). At both doses the mean success rate for intercourse attempts (SEP-Q3) was 58% and 68%, respectively, compared with 31% in the placebo group (P < 0.001), and 71% and 84% reported improved erections at the endpoint (GAQ), vs 33% on placebo (P < 0.001). Tadalafil was effective up to 36 h after dosing and was effective regardless of disease severity and causes, and in patients of all ages. The most frequent adverse events were headache, dyspepsia, back pain and myalgia. CONCLUSION: Tadalafil was an effective and well-tolerated treatment for ED.

Monitoring a clinical trial with multiple hypotheses concerning the treatment effect on a single primary endpoint.

In a number of clinical trials there is interest in testing more than one hypothesis concerning the treatment effect on a single primary endpoint. For instance, a sponsor of a trial to demonstrate that a test treatment (T) is non-inferior to an active control (R) may also be interested in showing that T is superior to R, if this is the case. Using the closed testing method for constructing tests of multiple hypotheses which control the multiple level of significance, we provide a framework for testing these hypotheses sequentially during a trial at pre-planned interim analyses.

Sample size recalculation using conditional power.

The sample size required to achieve a given power at a prespecified absolute difference in mean response may depend on one or more nuisance parameters, which are usually unknown. Proposed methods for using an internal pilot to recalculate the sample size using estimates of these parameters have been well studied. Most of these methods ignore the fact that data on the parameter of interest from within this internal pilot will contribute towards the value of the final test statistic. We propose a method which involves recalculating the target sample size by computing the number of further observations required to maintain the probability of rejecting the null hypothesis at the end of the study under the prespecified absolute difference in mean response conditional on the data observed so far. We do this within the framework of a two-group error-spending sequential test, modified so as to prevent inflation of the type I error rate.

Estimation following extension of a study on the basis of conditional power.

Proschan and Hunsberger (1) propose a method based on conditional power for designed extension of a study beyond its originally intended sample size. Their data-dependent sampling method can be viewed as a two-stage procedure in which the target total sample size is dependent upon the data observed at the first stage. We demonstrate that the maximum likelihood estimate of the parameter of interest upon completion may be biased, and that this bias is similar in direction and magnitude to that commonly associated with estimation following a group sequential test with predetermined target total sample size. Furthermore, we show how a bias adjusted estimate may be formed.

Estimating the sample size for a t-test using an internal pilot.

If the sample size for a t-test is calculated on the basis of a prior estimate of the variance then the power of the test at the treatment difference of interest is not robust to misspecification of the variance. We propose a t-test for a two-treatment comparison based on Stein's two-stage test which involves the use of an internal pilot to estimate variance and thus the final sample size required. We evaluate our procedure's performance and show that it controls the type I and II error rates more closely than existing methods for the same problem. We also propose a rule for choosing the size of the internal pilot, and show that this is reasonable in terms of the efficiency of the procedure.