MIBoost extends gradient boosting to multiple imputation by defining a single loss function that produces one set of selected variables across all imputed datasets.
Combination of direct and indirect evidence in mixed treatment comparisons
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
A contrast-space orthogonal projection framework yields an exact, covariance-aware, study-based decomposition of network meta-analysis estimators into direct and indirect evidence that exactly reconstructs the original estimates.
SIC is a prior-fitted network that amortizes Bayesian survival inference by pretraining on synthetic data generated from a controllable survival prior, delivering competitive or better performance than classical and deep models on real datasets especially in small-sample regimes.
Complete-case TMLE that includes an outcome-missingness model shows lower bias and greater robustness to positivity violations than multiple imputation approaches, while MI with CART yields lower RMSE and nominal coverage in simulations based on five missingness DAGs and a real epidemiological data.
citing papers explorer
-
MIBoost: A gradient boosting algorithm for variable selection after multiple imputation
MIBoost extends gradient boosting to multiple imputation by defining a single loss function that produces one set of selected variables across all imputed datasets.
-
Contrast-Space Projection for Network Meta-Analysis: An Exact and Invariant Study-Based Decomposition of Direct and Indirect Contributions
A contrast-space orthogonal projection framework yields an exact, covariance-aware, study-based decomposition of network meta-analysis estimators into direct and indirect evidence that exactly reconstructs the original estimates.
-
Survival In-Context: Amortized Bayesian Survival Analysis via Prior-Fitted Networks
SIC is a prior-fitted network that amortizes Bayesian survival inference by pretraining on synthetic data generated from a controllable survival prior, delivering competitive or better performance than classical and deep models on real datasets especially in small-sample regimes.
-
Causal Effect Estimation with TMLE: Handling Missing Data and Near-Violations of Positivity
Complete-case TMLE that includes an outcome-missingness model shows lower bias and greater robustness to positivity violations than multiple imputation approaches, while MI with CART yields lower RMSE and nominal coverage in simulations based on five missingness DAGs and a real epidemiological data.