Which covariates should be controlled in propensity score matching? Evidence from a simulation study

被引:36
|
作者
Nguyen Viet Cuong [1 ]
机构
[1] Wageningen Univ, Dev Econ Grp, Mansholt Grad Sch, NL-6700 AP Wageningen, Netherlands
关键词
impact evaluation; treatment effect; propensity score matching; covariate selection; Monte Carlo;
D O I
10.1111/stan.12000
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
Propensity score matching is a widely-used method to measure the effect of a treatment in social as well as medicine sciences. An important issue in propensity score matching is how to select conditioning variables in estimation of the propensity scores. It is commonly mentioned that variables which affect both program participation and outcomes are selected. Using Monte Carlo simulation, this paper shows that efficiency in estimation of the Average Treatment Effect on the Treated can be gained if all the available observed variables in the outcome equation are included in the estimation of propensity scores. This result still holds in the presence of non-sampling errors in the observed control variables.
引用
收藏
页码:169 / 180
页数:12
相关论文
共 50 条
  • [1] Balance of Controlled and Uncontrolled Covariates as a Function of Propensity Score Variable Selection Methods: A Simulation Study
    Wyss, R.
    Stedman, M. R.
    Brookhart, M. A.
    Rothman, K. J.
    Glynn, R.
    Poole, C.
    Seeger, J. D.
    Stuermer, T.
    [J]. PHARMACOEPIDEMIOLOGY AND DRUG SAFETY, 2011, 20 : S350 - S350
  • [2] Propensity score matching with time-dependent covariates
    Lu, B
    [J]. BIOMETRICS, 2005, 61 (03) : 721 - 728
  • [3] PROPENSITY SCORE MATCHING ANALYSIS FOR CAUSAL EFFECTS WITH MNAR COVARIATES
    Lu, Bo
    Ashmead, Robert
    [J]. STATISTICA SINICA, 2018, 28 (04) : 2005 - 2025
  • [4] Combining propensity score matching with additional adjustments for prognostic covariates
    Rubin, DB
    Thomas, N
    [J]. JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2000, 95 (450) : 573 - 585
  • [5] Combining propensity score matching with additional adjustments for prognostic covariates
    Rubin, D
    Thomas, N
    [J]. AMERICAN STATISTICAL ASSOCIATION - 1996 PROCEEDINGS OF THE EPIDEMIOLOGY SECTION, 1996, : 56 - 61
  • [6] Into which Region Should a Prophylactic Pancreatic Stent Be Inserted? A Propensity Score Matching Analysis
    Sugimoto, Mitsuru
    Takagi, Tadayuki
    Suzuki, Rei
    Konno, Naoki
    Asama, Hiroyuki
    Sato, Yuki
    Irie, Hiroki
    Nakamura, Jun
    Takasumi, Mika
    Hashimoto, Minami
    Kato, Tsunetaka
    Hikichi, Takuto
    Ohira, Hiromasa
    [J]. JOURNAL OF GASTROINTESTINAL AND LIVER DISEASES, 2020, 29 (03) : 399 - 405
  • [7] COMPARING PROPENSITY SCORE, PROPENSITY SCORE WITH COVARIATES AND GENETIC ALGORITHM METHODS FOR COVARIATE MATCHING IN OBSERVATIONAL STUDIES
    Claeys, C.
    Bakken, D. G.
    Wasserman, D.
    Spilman, J.
    [J]. VALUE IN HEALTH, 2014, 17 (03) : A200 - A200
  • [8] Propensity Score Matching and Unmeasured Covariate Imbalance: A Simulation Study
    Ali, M. Sanni
    Groenwold, Rolf H. H.
    Belitser, Svetlana V.
    Hoes, Arno W.
    de Boer, A.
    Klungel, Olaf H.
    [J]. PHARMACOEPIDEMIOLOGY AND DRUG SAFETY, 2014, 23 : 12 - 13
  • [9] PERFORMANCE OF PROPENSITY SCORE MATCHING IN SMALL SAMPLES - SIMULATION STUDY
    Cenzer, I
    Boscardin, W. J.
    Berger, K.
    [J]. VALUE IN HEALTH, 2018, 21 : S396 - S397
  • [10] Effective Learning During COVID-19: Multilevel Covariates Matching and Propensity Score Matching
    Guo S.
    Liu J.
    Wang Q.
    [J]. Annals of Data Science, 2022, 9 (05) : 967 - 982