Matching and Regression to the Mean in Difference-in-Differences Analysis

被引:152
|
作者
Daw, Jamie R. [1 ]
Hatfield, Laura A. [1 ]
机构
[1] Harvard Med Sch, Dept Hlth Care Policy, 180 Longwood Ave, Boston, MA 02115 USA
基金
美国国家卫生研究院;
关键词
Observational research; matching; difference-in-differences; MEDICARE BENEFICIARIES; PROGRAM; CARE; IMPACT; COSTS; ENROLLEES; OUTCOMES; QUALITY; MODELS;
D O I
10.1111/1475-6773.12993
中图分类号
R19 [保健组织与事业(卫生事业管理)];
学科分类号
摘要
Objective Data Sources To demonstrate regression to the mean bias introduced by matching on preperiod variables in difference-in-differences studies. Simulated data. Study Design Principal Findings We performed a Monte Carlo simulation to estimate the effect of a placebo intervention on simulated longitudinal data for units in treatment and control groups using unmatched and matched difference-in-differences analyses. We varied the preperiod level and trend differences between the treatment and control groups, and the serial correlation of the matching variables. We assessed estimator bias as the mean absolute deviation of estimated program effects from the true value of zero. When preperiod outcome level is correlated with treatment assignment, an unmatched analysis is unbiased, but matching units on preperiod outcome levels produces biased estimates. The bias increases with greater preperiod level differences and weaker serial correlation in the outcome. This problem extends to matching on preperiod level of a time-varying covariate. When treatment assignment is correlated with preperiod trend only, the unmatched analysis is biased, and matching units on preperiod level or trend does not introduce additional bias. Conclusions Researchers should be aware of the threat of regression to the mean when constructing matched samples for difference-in-differences. We provide guidance on when to incorporate matching in this study design.
引用
收藏
页码:4138 / 4156
页数:19
相关论文
共 50 条
  • [41] Design-based analysis in Difference-In-Differences settings with staggered adoption
    Athey, Susan
    Imbens, Guido W.
    [J]. JOURNAL OF ECONOMETRICS, 2022, 226 (01) : 62 - 79
  • [42] Postmenopausal Breast Cancer and Physical Function Change: A Difference-in-Differences Analysis
    Michael, Yvonne L.
    Wu, Chengyi
    Pan, Kathy
    Seguin-Fowler, Rebecca A.
    Garcia, David O.
    Zaslavsky, Oleg
    Chlebowski, Rowan T.
    [J]. JOURNAL OF THE AMERICAN GERIATRICS SOCIETY, 2020, 68 (05) : 1029 - 1036
  • [43] Trade liberalization and per capita income convergence: a difference-in-differences analysis
    Slaughter, MJ
    [J]. JOURNAL OF INTERNATIONAL ECONOMICS, 2001, 55 (01) : 203 - 228
  • [44] A spatial difference-in-differences analysis of the impact of sugarcane production on respiratory diseases
    Chagas, Andre L. S.
    Azzoni, Carlos R.
    Almeida, Alexandre N.
    [J]. REGIONAL SCIENCE AND URBAN ECONOMICS, 2016, 59 : 24 - 36
  • [45] Explaining persistence in online courses in higher education: a difference-in-differences analysis
    Lakhal, Sawsen
    Khechine, Hager
    Mukamurera, Josephine
    [J]. INTERNATIONAL JOURNAL OF EDUCATIONAL TECHNOLOGY IN HIGHER EDUCATION, 2021, 18 (01)
  • [46] Frontiers: A Simple Forward Difference-in-Differences Method
    Li, Kathleen T.
    [J]. MARKETING SCIENCE, 2024, 43 (02) : 267 - 279
  • [47] Abadie's semiparametric difference-in-differences estimator
    Houngbedji, Kenneth
    [J]. STATA JOURNAL, 2016, 16 (02): : 482 - 490
  • [48] A Negative Correlation Strategy for Bracketing in Difference-in-Differences
    Ye, Ting
    Keele, Luke
    Hasegawa, Raiden
    Small, Dylan S.
    [J]. JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2023,
  • [49] JUE Insight: Difference-in-differences with geocoded microdata
    Butts, Kyle
    [J]. JOURNAL OF URBAN ECONOMICS, 2023, 133
  • [50] Inference with difference-in-differences and other panel data
    Donald, Stephen G.
    Lang, Kevin
    [J]. REVIEW OF ECONOMICS AND STATISTICS, 2007, 89 (02) : 221 - 233