Causal inference with a quantitative exposure

被引:21
|
作者
Zhang, Zhiwei [1 ]
Zhou, Jie [1 ]
Cao, Weihua [1 ]
Zhang, Jun [2 ,3 ]
机构
[1] US FDA, Div Biostat, Off Surveillance & Biometr, Ctr Devices & Radiol Hlth, Silver Spring, MD USA
[2] Shanghai Jiao Tong Univ, Sch Med, Xinhua Hosp, MOE, Shanghai 200030, Peoples R China
[3] Shanghai Jiao Tong Univ, Sch Med, Xinhua Hosp, Shanghai Key Lab Childrens Environm Hlth, Shanghai 200030, Peoples R China
基金
美国国家卫生研究院;
关键词
Dose-response relationship; double robustness; inverse probability weighting; outcome regression; propensity function; propensity score; stratification; DOUBLY ROBUST ESTIMATION; PROPENSITY SCORE; PHYSICAL-ACTIVITY; BODY-COMPOSITION; MODELS; BIAS;
D O I
10.1177/0962280212452333
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
The current statistical literature on causal inference is mostly concerned with binary or categorical exposures, even though exposures of a quantitative nature are frequently encountered in epidemiologic research. In this article, we review the available methods for estimating the dose-response curve for a quantitative exposure, which include ordinary regression based on an outcome regression model, inverse propensity weighting and stratification based on a propensity function model, and an augmented inverse propensity weighting method that is doubly robust with respect to the two models. We note that an outcome regression model often imposes an implicit constraint on the dose-response curve, and propose a flexible modeling strategy that avoids constraining the dose-response curve. We also propose two new methods: a weighted regression method that combines ordinary regression with inverse propensity weighting and a stratified regression method that combines ordinary regression with stratification. The proposed methods are similar to the augmented inverse propensity weighting method in the sense of double robustness, but easier to implement and more generally applicable. The methods are illustrated with an obstetric example and compared in simulation studies.
引用
收藏
页码:314 / 335
页数:21
相关论文
共 50 条
  • [21] The Challenge of Causal Inference
    Dammann, Olaf
    Leviton, Alan
    [J]. ANNALS OF NEUROLOGY, 2010, 68 (05) : 770 - 770
  • [22] THE RATIONALITY OF CAUSAL INFERENCE
    SHULTZ, TR
    [J]. BEHAVIORAL AND BRAIN SCIENCES, 1991, 14 (03) : 503 - 503
  • [23] Causal Graph Inference
    Poilinca, Simona
    Parajuli, Jhanak
    Abreu, Giuseppe
    [J]. 2015 49TH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS AND COMPUTERS, 2015, : 1209 - 1213
  • [24] THE EROSION OF CAUSAL INFERENCE
    Weed, D. L.
    Alexander, D.
    Perez, V.
    [J]. AMERICAN JOURNAL OF EPIDEMIOLOGY, 2011, 173 : S187 - S187
  • [25] Prediction and causal inference
    Gagliardi, Luigi
    [J]. ACTA PAEDIATRICA, 2009, 98 (12) : 1890 - 1892
  • [26] THE FOUNDATIONS OF CAUSAL INFERENCE
    Pearl, Judea
    [J]. SOCIOLOGICAL METHODOLOGY, VOL 40, 2010, 40 : 75 - 149
  • [27] Indeterminism and causal inference
    Pedro, Inaki San
    Suarez, Mauricio
    [J]. TEOREMA, 2014, 33 (01): : 95 - 109
  • [28] The Future of Causal Inference
    Mitra, Nandita
    Roy, Jason
    Small, Dylan
    [J]. AMERICAN JOURNAL OF EPIDEMIOLOGY, 2022, 191 (10) : 1671 - 1676
  • [29] An Introduction to Causal Inference
    Pearl, Judea
    [J]. INTERNATIONAL JOURNAL OF BIOSTATISTICS, 2010, 6 (02):
  • [30] An introduction to causal inference
    Sobel, ME
    [J]. SOCIOLOGICAL METHODS & RESEARCH, 1996, 24 (03) : 353 - 379