In anticipation of Cyrus Mehta’s webinar next week on new predictive analytics tools for trial forecasting, we thought we might give you a few introductory notes on the nature and purpose of Predicted Interval Plots (better known as PIPs).
What are PIPs?
PIPs are a graphical tool used to predict the future course of a trial based on data accumulated by the time of interim analysis.
How are predictions made by PIPs different from efficacy/futility calculations?
Standard calculations of efficacy and futility rely on hypothesis testing. Although hypothesis testing can tell you whether or not to reject the null hypothesis, the null hypothesis typically asserts that the treatment difference is zero. Rejecting the null hypothesis does not provide any information about how great or small the treatment difference is. PIPs can make such predictions.
1: “[S]uppose the prespecified stopping rule has been met at an interim look but the investigators are still concerned about whether the treatment effect could change over a longer follow-up period, our approach can easily help the investigators evaluate their concerns... "
2: "[I]f the possibility of rejecting the null hypothesis at the end of the trial is fairly low even when the future data are generated under a very optimistic alternative hypothesis, then the investigators should consider stopping the trial early for futility to save resources and time.”
What tools are necessary to construct PIPs?
PIPs make predictions conditional upon data accrued during the course of a trial. A crucial element to creating PIPs is having access to reliable trial simulation tools.
How are PIPs constructed?
Find out by joining Cyrus Mehta’s webinar on Thursday July 24, at 10am Eastern Standard Time (4pm London, 5pm Europe). Cyrus will also be speaking about enrollment and event forecasting in time-to-event trials.