clinical trial planners

Abstract: lepidoptera is an open-source R and Python package for simulation from structural causal models with heterogeneous variable types. The package is built around a typed mechanism architecture, which separates the causal graph from the generating rule at each node and exposes each rule as an inspectable, serialisable object. A pre-built mechanism library covers all nine combinations of continuous, categorical, and ordinal parent and child types, removing the need for users to implement type-specific sampling from scratch. A vine copula mechanism estimates the full joint dependence structure from observed data using pair-copula constructions and the Rosenblatt conditional-simulation algorithm, supporting over twenty copula families. Individual-level counterfactual queries are supported through partial propagation, which freezes the random draws of unaffected nodes and replays only the downstream consequences of an intervention, thereby separating the individual treatment effect (ITE) estimand from the population-level average treatment effect (ATE) without additional model assumptions. An extension layer allows any pre-fitted predictive model to serve as a generative mechanism via a unified callable interface. Three worked illustrations spanning clinical trial planning, emergency-ward capacity analysis, and epidemiological mediation analysis demonstrate the package's scope.

Abstract: Models can be retrained as new data arrive, but deploying every new version risks replacing a good policy with a worse one. We study how to plan policy updates (i.e., meta-policy) before future candidates are trained, balancing the benefits of improvement against the risk of performance regression. Our offline meta-policy maximizes expected cumulative value subject to a budget on the expected number of updates that perform worse than the policies they replace. We estimate the value and risk of possible switches from historical learning trajectories, represent an update schedule as a path in a directed acyclic graph, and select a schedule using dynamic programming. A leading-order analysis identifies the signal-to-noise ratio of policy improvement as a key driver of update frequency, waiting times, and risk allocation: clearer improvements support earlier, more frequent updates, while noisier improvements call for longer waits or greater risk expenditure. Their asymptotic rates also reveal a diminishing marginal cost of achieving greater safety over time. Experiments on synthetic and clinical trial data illustrate the performance--risk tradeoff and compare our method with alternative baselines.