Stata新命令-pdslasso：众多控制变量和工具变量如何挑选？

全文阅读：/news/ccada6e4c41df.html

目录

Stata package: pdslassoInstallationHelp filesAcknowledgementsCitationAuthorsIssues and questions

Stata package: pdslasso

pdslassoandivlassoare routines for estimating structural parameters in linear models with many controls and/or instruments. The routines use methods for estimating sparse high-dimensional models, specifically the lasso (Least Absolute Shrinkage and Selection Operator,Tibshirani 1996) and the square-root-lasso (Belloni et al.,).

These estimators are used to select controls (pdslasso) and/or instruments (ivlasso) from a large set of variables (possibly numbering more than the number of observations), in a setting where the researcher is interested in estimating the causal impact of one or more (possibly endogenous) causal variables of interest.

Two approaches are implemented inpdslassoandivlasso:

Thepost-double-selectionmethodology of Belloni et al. (,,,,).Thepost-regularizationmethodology ofChernozhukov, Hansen and Spindler ().

For instrumental variable estimation, `ivlasso implements weak-identification-robust hypothesis tests and confidence sets using theChernozhukov et al. ()sup-score test.

The implemention of these methods inpdslassoandivlassorequire the Stata programrlasso(available in the separate Stata modulelassopack), which provides lasso and square root-lasso estimation with data-driven penalization.

全文阅读：/news/ccada6e4c41df.html

如果觉得《Stata新命令-pdslasso：众多控制变量和工具变量如何挑选？》对你有帮助，请点赞、收藏，并留下你的观点哦！