Abstract:
|
With the growing shift towards precision medicine, there is renewed interest in determining whether there are differential treatment effects in subgroups of trial participants. Intrinsic to this problem is that any assessment of differential treatment effect is predicated on being able to estimate the treatment response accurately while satisfying constraints of balancing the risk of overlooking an important subgroup with the potential to make a decision based on false discovery. While regression models have been widely used to improve accuracy of subgroup parameter estimates there is still a possibility that it can lead to excessively conservative or anti-conservative results due to restrictive prior choice or model misspecification. To address this issue, we investigate the use of Dirichlet process priors to create semiparametric models that represent uncertainty in the prior distribution for the overall response while accommodating heterogeneity among individual subgroups. We evaluated the two models through simulations measuring bias, mean squared error, and coverage probability.
|