{"title":"利用倾向得分校准提高双重/偏差机器学习的有限样本性能","authors":"Daniele Ballinari, Nora Bearth","doi":"arxiv-2409.04874","DOIUrl":null,"url":null,"abstract":"Machine learning techniques are widely used for estimating causal effects.\nDouble/debiased machine learning (DML) (Chernozhukov et al., 2018) uses a\ndouble-robust score function that relies on the prediction of nuisance\nfunctions, such as the propensity score, which is the probability of treatment\nassignment conditional on covariates. Estimators relying on double-robust score\nfunctions are highly sensitive to errors in propensity score predictions.\nMachine learners increase the severity of this problem as they tend to over- or\nunderestimate these probabilities. Several calibration approaches have been\nproposed to improve probabilistic forecasts of machine learners. This paper\ninvestigates the use of probability calibration approaches within the DML\nframework. Simulation results demonstrate that calibrating propensity scores\nmay significantly reduces the root mean squared error of DML estimates of the\naverage treatment effect in finite samples. We showcase it in an empirical\nexample and provide conditions under which calibration does not alter the\nasymptotic properties of the DML estimator.","PeriodicalId":501293,"journal":{"name":"arXiv - ECON - Econometrics","volume":"23 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Improving the Finite Sample Performance of Double/Debiased Machine Learning with Propensity Score Calibration\",\"authors\":\"Daniele Ballinari, Nora Bearth\",\"doi\":\"arxiv-2409.04874\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Machine learning techniques are widely used for estimating causal effects.\\nDouble/debiased machine learning (DML) (Chernozhukov et al., 2018) uses a\\ndouble-robust score function that relies on the prediction of nuisance\\nfunctions, such as the propensity score, which is the probability of treatment\\nassignment conditional on covariates. Estimators relying on double-robust score\\nfunctions are highly sensitive to errors in propensity score predictions.\\nMachine learners increase the severity of this problem as they tend to over- or\\nunderestimate these probabilities. Several calibration approaches have been\\nproposed to improve probabilistic forecasts of machine learners. This paper\\ninvestigates the use of probability calibration approaches within the DML\\nframework. Simulation results demonstrate that calibrating propensity scores\\nmay significantly reduces the root mean squared error of DML estimates of the\\naverage treatment effect in finite samples. We showcase it in an empirical\\nexample and provide conditions under which calibration does not alter the\\nasymptotic properties of the DML estimator.\",\"PeriodicalId\":501293,\"journal\":{\"name\":\"arXiv - ECON - Econometrics\",\"volume\":\"23 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - ECON - Econometrics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.04874\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - ECON - Econometrics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.04874","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Improving the Finite Sample Performance of Double/Debiased Machine Learning with Propensity Score Calibration
Machine learning techniques are widely used for estimating causal effects.
Double/debiased machine learning (DML) (Chernozhukov et al., 2018) uses a
double-robust score function that relies on the prediction of nuisance
functions, such as the propensity score, which is the probability of treatment
assignment conditional on covariates. Estimators relying on double-robust score
functions are highly sensitive to errors in propensity score predictions.
Machine learners increase the severity of this problem as they tend to over- or
underestimate these probabilities. Several calibration approaches have been
proposed to improve probabilistic forecasts of machine learners. This paper
investigates the use of probability calibration approaches within the DML
framework. Simulation results demonstrate that calibrating propensity scores
may significantly reduces the root mean squared error of DML estimates of the
average treatment effect in finite samples. We showcase it in an empirical
example and provide conditions under which calibration does not alter the
asymptotic properties of the DML estimator.