Survival data are most frequently analyzed by the intention-to-treat principle. However, presenting a compliance-adjusted analysis alongside the primary analysis can provide an insight into the effect of the treatment for those individuals actually complying with their randomized intervention. There are a number of methods for this type of analysis. Loeys and Goetghebeur (2003) use proportional hazards techniques to provide an estimate of the treatment effect for compliers when compliance is measured on an all-or-nothing scale. This methodology is here made available through a new Stata command, stcomply.
CuzickJ., EdwardsR., and SegnanN.1997. Adjusting for noncompliance and contamination in randomized clinical trials. Statistics in Medicine16: 1017–1029.
2.
FrangakisC. E., and RubinD.B.1999. Addressing complications of intention-to-treat analysis in the combined presence of all-or-none treatment-noncompliance and subsequent missing outcomes. Biometrika86: 365–379.
3.
LoeysT., and GoetghebeurE.2003. A causal proportional hazards estimator for the effect of treatment actually received in a randomized trial with all-or-nothing compliance. Biometrics59: 100–105.
4.
RobinsJ. M., and TsiatisA.A.1991. Correcting for noncompliance in randomized trials using rank preserving structural failure time models. Communications in Statistics Theory and Methods20: 2609–2631.
5.
SommerA., and ZegerS.L.1991. On estimating efficacy from clinical trials. Statistics in Medicine10: 45–52.
6.
The Multicentre Aneurysm Screening Study Group.2002. The Multicentre Aneurysm Screening Study (MASS) into the effect of abdominal aortic aneurysm screening on mortality in men: a randomized controlled trial. Lancet360: 1531–1539.
7.
WhiteI. R., WalkerS., and BabikerA.2002. strbee: Randomization-based efficacy estimator. Stata Journal2(2): 140–150.
