Deep Neural Networks Guided Ensemble Learning for Point Estimation

Abstract

AbstractIn modern statistics, interests shift from pursuing the uniformly minimum variance unbiased estimator to reducing mean squared error (MSE) or residual squared error. Shrinkage-based estimation and regression methods offer better prediction accuracy and improved interpretation. However, the characterization of such optimal statistics in terms of minimizing MSE remains open and challenging in many problems, for example, estimating the treatment effect in adaptive clinical trials with pre-planned modifications to design aspects based on accumulated data. From an alternative perspective, we propose a deep neural network based automatic method to construct an improved estimator from existing ones. Theoretical properties are studied to provide guidance on applicability of our estimator to seek potential improvement. Simulation studies demonstrate that the proposed method has considerable finite-sample efficiency gain compared to several common estimators. In the Adaptive COVID-19 Treatment Trial (ACTT) as a motivating example, our ensemble estimator essentially contributes to a more ethical and efficient adaptive clinical trial with fewer patients enrolled. The proposed framework can be generally applied to various statistical problems, and can serve as a reference measure to guide statistical research.Keywords: Deep learningEfficiencyImproved statisticsDisclaimerAs a service to authors and researchers we are providing this version of an accepted manuscript (AM). Copyediting, typesetting, and review of the resulting proofs will be undertaken on this manuscript before final publication of the Version of Record (VoR). During production and pre-press, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal relate to these versions also. Supplemental MaterialsSupplementary Materials including Appendices, Tables and Figures referenced in this article are available online. The R code and a help file to replicate results in the main article are available at https://github.com/tian-yu-zhan/DNN_Point_Estimation.This manuscript was supported by AbbVie Inc. AbbVie participated in the review and approval of the content. Tianyu Zhan is employed by AbbVie Inc., Haoda Fu is employed by Eli Lilly and Company, and Jian Kang is Professor in the Department of Biostatistics at the University of Michigan, Ann Arbor. Kang’s research was partially supported by NIH R01 GM124061 and R01 MH105561. All authors may own AbbVie stock.Conflict of InterestNo potential competing interest was reported by the authors.AcknowledgementsThe authors thank the editorial board and reviewers for their constructive comments.FundingThe author(s) reported there is no funding associated with the work featured in this article.