To study whether air pollution is detrimental to reproductive development is imperative. In the absence of randomized trials to study the effects of air pollution on human health, data from observational studies have been utilized in which the researchers attempted to capture the causal associations between air pollution and the health outcomes. Many of these studies rely on parametric assumptions which may be limiting. In this tutorial, we explain and implement the nonparametric empirical likelihood (EL) Algorithm within the causal inference framework of a classic methodology and a newer technique based on machine learning tools. We show the competitive results of the assumption free EL in simulations. We also apply the developed methods to study the causal association between PM2.5 and NO2 exposure and anogenital distance at birth, a marker of androgen activity.
RosenbaumPRRubinDB. The central role of the propensity score in observational studies for causal effects. Biometrika1983; 70: 41–55.
2.
ImaiKVan DykDA. Causal inference with general treatment regimes: generalizing the propensity score. J Am Stat Assoc2004; 99: 854–866.
3.
KangJDYSchaferJL. Demystifying double robustness: a comparison of alternative strategies for estimating a population mean from incomplete data. Stat Sci2007; 22: 523–539.
4.
RobinsJSuedMLei-GomezQ, et al.Comment: Performance of double-robust estimators when “inverse probability” weights are highly variable. Stat Sci2007; 22: 544–559.
5.
RobinsJMMarkSDNeweyWK. Estimating exposure effects by modelling the expectation of exposure conditional on confounders. Biometrics1992; 48: 479–495.
6.
MakarMAntonelliJDiQ, et al.Estimating the causal effect of low levels of fine particulate matter on hospitalization. Epidemiology2017; 28: 627–634.
7.
GillRDRobinsJM. Causal inference for complex longitudinal data: the continuous case. Ann Stat2001; 29: 1785–1811.
8.
HiranoKImbensGW. Applied bayesian modeling and causal inference from incomplete-data perspectives. Chichester, UK: John Wiley & Sons, Ltd, 20047384chapter 7.
9.
JohnsonBATsiatisAA. Estimating mean response as a function of treatment duration in an observational study, where duration may be informatively censored. Biometrics2004; 60: 315–323.
10.
JohnsonBATsiatisAA. Semiparametric inference in observational duration-response studies, with duration possibly right-censored. Biometrika2005; 92: 605–618.
11.
LokJGillRVan Der VaartA, et al.Estimating the causal effect of a time-varying treatment on time-to-event using structural nested failure time models. Stat Neerl2004; 58: 271–295.
12.
MurphySAvan der LaanMJRobinsJM, et al.Marginal mean models for dynamic regimes. J Am Stat Assoc2001; 96: 1410–1423.
13.
ZhuYCoffmanDLGhoshD. A boosting algorithm for estimating generalized propensity scores with continuous treatments. J Causal Inference2015; 3: 25–40.
14.
SchwabPLinhardtLBauerS, et al.Learning counterfactual representations for estimating individual dose–response curves. In Proceedings of the AAAI conference on artificial ontelligence. Vol. 34, 2020, pp.5612–5619.
15.
WangXLyuSWuX, et al.Generalization bounds for estimating causal effects of continuous treatments. Adv Neural Inf Process Syst2022; 35: 8605–8617.
16.
BahadoriTTchetgenETHeckermanD. End-to-end balancing for causal continuous treatment-effect estimation. In International conference on machine learning. PMLR, 2022, pp.1313–1326.
GreiferNHulingJDChenG. Independence weights for causal inference with continuous treatments. J Am Stat Assoc2024; 119: 1657–1670.
19.
OwenA. Empirical likelihood ratio confidence regions. Ann Stat1990; 18: 90–120.
20.
RobinsJMAngel HernanMBrumbackB. Marginal structural models and causal inference in epidemiology. Epidemiology2000; 11: 550–560.
21.
LeeBKLesslerJStuartEA. Improving propensity score weighting using machine learning. Stat Med2010; 29: 337–346.
22.
McCaffreyDFRidgewayGMorralAR. Propensity score estimation with boosted regression for evaluating causal effects in observational studies. Psychol Methods2004; 9: 403.
23.
WestreichDLesslerJFunkMJ. Propensity score estimation: machine learning and classification methods as alternatives to logistic regression. J Clin Epidemiol2010; 63: 826.
24.
QinJZhangB. Empirical-likelihood-based inference in missing response problems and its application in observational studies. J R Stat Soc B: Stat Methodol2007; 69: 101–122.
25.
TanZ. A distributional approach for causal inference using propensity scores. J Am Stat Assoc2006; 101: 1619–1637.
26.
RobinsJMRotnitzkyAZhaoLP. Estimation of regression coefficients when some regressors are not always observed. J Am Stat Assoc1994; 89: 846–866.
27.
HollandPW. Statistics and causal inference. J Am Stat Assoc1986; 81: 945–960.
28.
ImbensGWRubinDB. Causal inference in statistics, social, and biomedical sciences. Cambridge, UK: Cambridge University Press, 2015.
29.
RubinDB. Estimating causal effects of treatments in randomized and nonrandomized studies. J Educ Psychol1974; 66: 688.
30.
RubinDB. Inference and missing data. Biometrika1976; 63: 581–592.
SeamanSGalatiJJacksonD, et al.What is meant by “missing at random”?, 2013.
33.
JoffeMMRosenbaumPR. Invited commentary: propensity scores. Am J Epidemiol1999; 150: 327–333.
34.
RosenbaumPRRubinDB. Reducing bias in observational studies using subclassification on the propensity score. J Am Stat Assoc1984; 79: 516–524.
35.
OwenAB. Empirical likelihood ratio confidence intervals for a single functional. Biometrika1988 Jun; 75: 237–249.
36.
LiGWangQH. Empirical likelihood regression analysis for right censored data. Stat Sin2003; 13: 51–68.
37.
QinJLawlessJ. Empirical likelihood and general estimating equations. Ann Stat1994; 22: 300–325.
38.
SharghiSStollKNingW. Statistical inferences for missing response problems based on modified empirical likelihood. Stat Pap2024; 65: 4079.
39.
WangQHJingBY. Empirical likelihood for a class of functionals of survival distribution with censored data. Ann Inst Stat Math2001; 53: 517–527.
40.
ChenSX. Empirical likelihood-based kernel density estimation. Aust J Stat1997; 39: 47–56.
41.
ParzenE. On estimation of a probability density function and mode. Ann Math Stat1962; 33: 1065–1076.
42.
RosenblatM. Remarks on some nonparametric estimates of a density function. Ann Math Stat1956; 27: 832–837.
43.
BickelPJGötzeFvan ZwetWR. Resampling fewer than n observations: gains, losses, and remedies for losses. New York, NY, USA: Springer, 2012.
44.
ChatterjeeALahiriSN. Bootstrapping lasso estimators. J Am Stat Assoc2011; 106: 608–625.
45.
WeiYWangYWuX, et al.Causal effects of air pollution on mortality rate in Massachusetts. Am J Epidemiol2020; 189: 1316–1323.
46.
BellMLEbisuKPengRD, et al.Seasonal and regional short-term effects of fine particles on hospital admissions in 202 US counties, 1999–2005. Am J Epidemiol2008; 168: 1301–1310.
47.
BravoMAEbisuKDominiciF, et al.Airborne fine particles and risk of hospital admissions for understudied populations: effects by urbanicity and short-term cumulative exposures in 708 U.S. counties. Environ Health Perspect2017; 125: 594–601.
48.
DominiciFMcDermottAZegerSL, et al.National maps of the effects of particulate matter on mortality: exploring geographical variation. Environ Health Perspect2003; 111: 39–44.
49.
DominiciFPengRDBellML, et al.Fine particulate air pollution and hospital admission for cardiovascular and respiratory diseases. JAMA2006; 295: 1127–1134.
50.
RichDQLiuKZhangJ, et al.Differences in birth weight associated with the 2008 Beijing olympics air pollution reduction: results from a natural experiment. Environ Health Perspect2015; 123: 880–887.
51.
BekkarBPachecoSBasuR, et al.Association of air pollution and heat exposure with preterm birth, low birth weight, and stillbirth in the US: a systematic review. JAMA Netw Open2020; 3: e208243.
52.
BellMLEbisuKBelangerK. Ambient air pollution and low birth weight in Connecticut and Massachusetts. Environ Health Perspect2007; 115: 1118–1124.
53.
BobakM. Outdoor air pollution, low birth weight, and prematurity. Environ Health Perspect2000; 108: 173–176.
54.
GouveiaNBremnerSANovaesHMD. Association between ambient air pollution and birth weight in São Paulo, Brazil. J Epidemiol Commun Health2004; 58: 11–17.
55.
LiuYXuJChenD, et al.The association between air pollution and preterm birth and low birth weight in Guangdong, China. BMC Public Health2019; 19: 1–10.
56.
MannesTJalaludinBMorganG, et al.Impact of ambient air pollution on birth weight in Sydney, Australia. Occup Environ Med2005; 62: 524–530.
57.
Morello-FroschRJesdaleBMSaddJL, et al.Ambient air pollution exposure and full-term birth weight in California. Environ Health2010; 9: 1–13.
58.
SarizadehRDastoorpoorMGoudarziG, et al.The association between air pollution and low birth weight and preterm labor in Ahvaz, Iran. Int J Womens Health2020; 12: 313–325.
59.
ShangLHuangLYangL, et al.Impact of air pollution exposure during various periods of pregnancy on term birth weight: a large-sample, retrospective population-based cohort study. Environ Sci Pollut Res2021; 28: 3296–3306.
60.
SteinleSJohnstonHJLohM, et al.In utero exposure to particulate air pollution during pregnancy: impact on birth weight and health through the life course. Int J Environ Res Public Health2020; 17: 8948.
61.
StiebDMChenLEshoulM, et al.Ambient air pollution, birth weight and preterm birth: a systematic review and meta-analysis. Environ Res2012; 117: 100–111.
62.
UwakIOlsonNFuentesA, et al.Application of the navigation guide systematic review methodology to evaluate prenatal exposure to particulate matter air pollution and infant birth weight. Environ Int2021; 148: 106378.
63.
BarrettESSharghiSThurstonSW, et al.Associations of exposure to air pollution during the male programming window and mini-puberty with anogenital distance and penile width at birth and at 1 year of age in the multicenter U.S. tides cohort. Environ Health Perspect2023; 131: 117001.
64.
BrookhartMASchneeweissSRothmanKJ, et al.Variable selection for propensity score models. Am J Epidemiol2006; 163: 1149–1156.
65.
DaoudaMHennemanLKioumourtzoglouMA, et al.Association between county-level coal-fired power plant pollution and racial disparities in preterm births from 2000 to 2018. Environ Res Lett2021; 16: 034055.
66.
DeguenSKihal-TalantikiteWGillesM, et al.Are the effects of air pollution on birth weight modified by infant sex and neighborhood socioeconomic deprivation? A multilevel analysis in Paris (France). PLoS One2021; 16: e0247699.
67.
LamichhaneDKLeeSYAhnK, et al.Quantile regression analysis of the socioeconomic inequalities in air pollution and birth weight. Environ Int2020; 142: 105875.
68.
LiuJClarkLPBechleMJ, et al.Disparities in air pollution exposure in the United States by race/ethnicity and income, 1990–2010. Environ Health Perspect2021; 129: 127005.
69.
PattersonWBGlassonJNaikN, et al.Prenatal exposure to ambient air pollutants and early infant growth and adiposity in the Southern California Mother’s Milk Study. Environ Health2021; 20: 67.
70.
KainzKGreiferNGivensA, et al.Improving causal inference: recommendations for covariate selection and balance in propensity score methods. J Soc Social Work Res2017; 8: 279–303.
71.
BelitserSVMartensEPPestmanWR, et al.Measuring balance and model selection in propensity score methods. Pharmacoepidemiol Drug Saf2011; 20: 1115–1129.
72.
PearlJ. On a class of bias-amplifying variables that endanger effect estimates. arXiv preprint arXiv:1203.3503, 2012.
73.
AustinPC. An introduction to propensity score methods for reducing the effects of confounding in observational studies. Multivariate Behav Res2011; 46: 399–424.
