English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Selection of covariates is crucial in the estimation of average treatmenteffects given observational data with high or even ultra-high dimensionalpretreatment variables. Existing methods for this problem typically assumesparse linear models for both outcome and univariate treatment, and cannothandle situations with ultra-high dimensional covariates. In this paper, wepropose a new covariate selection strategy called double screening prioradaptive lasso (DSPAL) to select confounders and predictors of the outcome formultivariate treatments, which combines the adaptive lasso method with themarginal conditional (in)dependence prior information to select targetcovariates, in order to eliminate confounding bias and improve statisticalefficiency. The distinctive features of our proposal are that it can be appliedto high-dimensional or even ultra-high dimensional covariates for multivariatetreatments, and can deal with the cases of both parametric and nonparametricoutcome models, which makes it more robust compared to other methods. Ourtheoretical analyses show that the proposed procedure enjoys the sure screeningproperty, the ranking consistency property and the variable selectionconsistency. Through a simulation study, we demonstrate that the proposedapproach selects all confounders and predictors consistently and estimates themultivariate treatment effects with smaller bias and mean squared errorcompared to several alternatives under various scenarios. In real dataanalysis, the method is applied to estimate the causal effect of athree-dimensional continuous environmental treatment on cholesterol level andenlightening results are obtained.

A New Covariate Selection Strategy for High Dimensional Data in Causal Effect Estimation with Multivariate Treatments