Model-Assisted Inference for Covariate-Specific Treatment Effects with High-dimensional Data
نویسندگان
چکیده
Covariate-specific treatment effects (CSTEs) represent heterogeneous across subpopulations defined by certain selected covariates. In this article, we consider marginal structural models where CSTEs are linearly represented using a set of basis functions the We develop new approach in high-dimensional settings to obtain not only doubly robust point estimators CSTEs, but also model-assisted confidence intervals, which valid when propensity score model is correctly specified an outcome regression may be misspecified. With linear and discrete covariates, both intervals for CSTEs. contrast, from existing methods specified. establish asymptotic properties proposed associated intervals. present simulation studies empirical applications demonstrate advantages method compared with competing ones.
منابع مشابه
Statistical Inference for High Dimensional Data
STATISTICAL INFERENCE FOR HIGH DIMENSIONAL DATA
متن کاملInference on Treatment Effects after Selection amongst High-dimensional Controls
We propose robust methods for inference on the effect of a treatment variable on a scalar outcome in the presence of very many controls. Our setting is a partially linear model with possibly non-Gaussian and heteroscedastic disturbances where the number of controls may be much larger than the sample size. To make informative inference feasible, we require the model to be approximately sparse; t...
متن کاملMethods for regression analysis in high-dimensional data
By evolving science, knowledge and technology, new and precise methods for measuring, collecting and recording information have been innovated, which have resulted in the appearance and development of high-dimensional data. The high-dimensional data set, i.e., a data set in which the number of explanatory variables is much larger than the number of observations, cannot be easily analyzed by ...
متن کاملCovariate selection in high-dimensional propensity score analyses of treatment effects in small samples.
To reduce bias by residual confounding in nonrandomized database studies, the high-dimensional propensity score (hd-PS) algorithm selects and adjusts for previously unmeasured confounders. The authors evaluated whether hd-PS maintains its capabilities in small cohorts that have few exposed patients or few outcome events. In 4 North American pharmacoepidemiologic cohort studies between 1995 and ...
متن کاملBayesian inference for longitudinal data with non-parametric treatment effects.
We consider inference for longitudinal data based on mixed-effects models with a non-parametric Bayesian prior on the treatment effect. The proposed non-parametric Bayesian prior is a random partition model with a regression on patient-specific covariates. The main feature and motivation for the proposed model is the use of covariates with a mix of different data formats and possibly high-order...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Statistica Sinica
سال: 2024
ISSN: ['1017-0405', '1996-8507']
DOI: https://doi.org/10.5705/ss.202022.0089