STAT 509 Lesson 10: Late Phase Studies - Interim Analyses

Vocabulary-style flashcards covering interim monitoring, group sequential methods (Pocock, Haybittle-Peto, O'Brien-Fleming), alpha spending functions, futility, and DSMB/IRB procedures.

Frequentist interim-monitoring focus

Control the overall Type I error rate while repeatedly examining accumulating data.

DSMB framework

Data Safety Monitoring Boards use interim information to assess participant safety, efficacy, trial conduct, and whether a study should continue or change.

Group sequential analysis

A design in which only a few prescheduled statistical analyses are conducted as data accumulate.

$$R$$

Number of planned analyses, including interim analyses and the final analysis.

Boundary point/critical value

A prespecified cutoff used to decide whether evidence is sufficiently strong to reject the null hypothesis and stop the trial.

Group sequential stopping principle

At an interim analysis, terminate with rejection of $H_0$ when the test statistic crosses the prespecified rejection boundary.

Boundary-selection objective

Choose boundaries so the overall significance level across all analyses does not exceed the desired alpha.

Pocock approach

Uses the same significance level/critical boundary at every scheduled analysis; it provides the best chance of early trial termination but uses a stricter significance level for the final analysis.

Haybittle-Peto approach

Uses a very stringent boundary for interim looks and approximately the conventional boundary at the final analysis.

O'Brien-Fleming approach

Uses extremely stringent early boundaries that gradually relax, leaving the final analysis close to the conventional alpha level.

Example 10.1 Primary Endpoint

Presence/absence of tumor shrinkage; identified in the lesson as a surrogate variable.

Alpha spending function approach

A flexible interim-monitoring framework developed to overcome fixed-number and equal-spacing restrictions of traditional group sequential plans.

Information fraction ($\tau$)

The fraction of the trial's total planned statistical information available at an interim analysis.

Information fraction for fixed-sample mean comparison

$\tau = n/N$, where $n$ is current sample size and $N$ is target sample size.

Information fraction for time-to-event trial

$\tau = d/D$, where $d$ is the number of events observed so far and $D$ is the target total number of events.

Alpha spending function $\alpha(\tau)$

An increasing function describing how much of the total Type I error has been spent by information fraction $\tau$, where $\alpha(0) = 0$ and $\alpha(1) = \text{alpha}$.

Early stopping bias

The phenomenon where treatment-effect estimates are biased when a trial terminates early; bias is larger the earlier the stopping decision is made.

Futility assessment

A plan to terminate a trial when accumulating results indicate that additional enrollment is unlikely to change the ultimate conclusion.

Curtailed sampling

Another term for stopping a trial early because continuation is unlikely to alter the conclusion.

Unconditional power

Probability, calculated at the beginning of a trial, of obtaining statistical significance at a prespecified alpha under a prespecified alternative treatment effect.

Conditional power

Probability of rejecting $H_0$ at the end of the trial conditional on the data already observed and an assumption about future outcomes/true effect.

Adaptive design

A design that prespecifies how study features (such as sample size) may change in response to observed interim results while maintaining statistical validity.

Multi-center trial

A trial conducted at multiple centers with one or more clinical investigators at each location, often necessary for adequate enrollment in rare diseases.

DSMB independence

The requirement that the board be financially and scientifically independent of study investigators to ensure objective decision-making.

DSMB masking

The principle that the board should NOT be masked to treatment assignment when evaluating the trial.

DSMB reporting line

Reports directly to the trial sponsor (e.g., NIH or company) rather than to the study investigators.