ebct: Using entropy balancing for continuous treatments to estimate dose–response functions and their derivatives

Stefan Tübbicke

Stata Journal, 2023, vol. 23, issue 3, 709-729

Abstract: Interest in evaluating dose–response functions of continuous treatments has been increasing recently. To facilitate the estimation of causal effects in this setting, I introduce the ebct command for the estimation of dose–response functions and their derivatives using entropy balancing for continuous treatments. First, balancing weights are estimated by numerically solving a globally convex optimization problem. These weights eradicate Pearson correlations between co- variates and the treatment variable. Because simple uncorrelatedness may be insufficient to yield consistent estimates in the next step, higher moments of the treatment variable can be rendered uncorrelated with covariates. Second, the weights are used in local linear kernel regressions to estimate the dose–response function or its derivative. To perform statistical inference, I use a bootstrap pro- cedure. The command also provides the option of producing publication-quality graphs for the estimated relationships.

Keywords: ebct; entropy balancing; continuous treatments; balancing weights; observational studies; dose–response functions (search for similar items in EconPapers)
Date: 2023
Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj23-3/st0726/
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.stata-journal.com/article.html?article=st0726 link to article purchase

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:tsj:stataj:v:23:y:2023:i:3:p:809-729

Ordering information: This journal article can be ordered from
http://www.stata-journal.com/subscription.html

DOI: 10.1177/1536867X231196291

Access Statistics for this article

Stata Journal is currently edited by Nicholas J. Cox and Stephen P. Jenkins

More articles in Stata Journal from StataCorp LLC
Bibliographic data for series maintained by Christopher F. Baum () and Lisa Gilmore ().