The use of propensity scores as a method to promote causality in studies that cannot use random assignment has increased dramatically since its original publication in 1983. While the utility of these approaches is important, the concepts underlying their use are complex. The purpose of this article is to provide a basic tutorial for conducting analyses using propensity scores and what researchers should be aware of in reading papers that choose propensity scores as a method, as well as in conducting their own research. In addition to the explanations given, examples are presented, based on actual studies, which illustrate the use of propensity scores for regression adjustment, stratification, and matching. The syntax, datasets, and output used for these examples are available on http://jea.sagepub.com/content/early/recent for readers to download and follow.
AustinP. C. (2011). An introduction to propensity score methods for reducing the effects of confounding in observational studies. Multivariate Behavioral Research, 46, 399-424. doi:10.1080/00273171.2011.568786
2.
BaiH. (2011). Using propensity score analysis for making causal claims in research articles. Educational Psychology Review, 23, 273-278. doi:10.1007/s10648-011-9164-9
3.
BenowitzN.LessovschlaggarC.SwanG.JacobiiiP. (2006). Female sex and oral contraceptive use accelerate nicotine metabolism. Clinical Pharmacology & Therapeutics, 79, 480-488. doi:10.1016/j.clpt.2006.01.008
4.
BerensonA. B.RadeckiC. M.GradyJ. J.RickertV. I.ThomasA. (2001). A prospective, controlled study of the effects of hormonal contraception on bone mineral density. Obstetrics & Gynecology, 98, 576-582.
BhattacharyaJ.VogtW. B. (2007). Do instrumental variables belong in propensity scores?Cambridge, MA: National Bureau of Economic Research.
7.
BiglanA.DuncanT.AryD.SmolkowskiK. (1995). Peer and parental influences on adolescent tobacco use. Journal of Behavioral Medicine, 18, 315-330. doi:10.1007/bf01857657
8.
BrookhartM. A.SchneeweissS.RothmanK. J.GlynnR. J.AvornJ.StürmerT. (2006). Variable selection for propensity score models. American Journal of Epidemiology, 163, 1149-1156. doi:10.1093/aje/kwj149
9.
CaliendoM.KopeinigS. (2008). Some practical guidance for the implementation of propensity score matching. Journal of Economic Surveys, 22, 31-72.
10.
CleophasT.ZwindermanA. (2012). Propensity score matching. In CleophasT. J.ZwindermanA. H. (Eds.), Statistics applied to clinical studies (pp. 329-336). Netherlands: Springer.
11.
CorreaM. G.Gomes CamposM. L.César-NetoJ. B.CasatiM. Z.NocitiF. H.SallumE. A. (2009). Histometric evaluation of bone around titanium implants with different surface treatments in rats exposed to cigarette smoke inhalation. Clinical Oral Implants Research, 20, 588-593. doi:10.1111/j.1600-0501.2008.01695.x
12.
D’AgostinoR. B. (1998). Propensity score methods for bias reduction in the comparison of a treatment to a nonrandomized control group. Statistics in Medicine, 17, 2265-2281. doi:10.1002/(SICI)1097-0258(19981015)17:19<2265::AID-SIM918>3.0.CO;2-B
13.
D’AgostinoR. B. (2007). Propensity scores in cardiovascular research. Circulation, 115, 2340-2343. doi:10.1161/circulationaha.105.594952
14.
DornL. D. (2003). Smoking and metabolic complications in adolescent girls: Funded by NIDA (NIH. 2004-2009). Washington, DC: U.S. Department of Health & Human Services.
15.
DornL. D.BealS. J.KalkwarfH.PabstS.NollJ. G.SusmanE. J. (2013). Longitudinal impact of substance use and depressive symptoms on bone accrual among girls aged 11-19 years. Journal of Adolescent Health, 52, 393-399. doi:10.1016/j.jadohealth.2012.10.005
16.
DornL. D.SusmanE. J.PabstS.HuangB.KalkwarfH.GrimesS. (2008). Association of depressive symptoms and anxiety with bone mass and density in ever-smoking and never-smoking adolescent girls. Archives of Pediatrics & Adolescent Medicine, 162, 1181-1188. doi:10.1001/archpedi.162.12.1181
17.
ElliotJ. R.GilchristN. L.WellsJ. E. (1996). The effect of socioeconomic status on bone density in a male Caucasian population. Bone, 18, 371-373. Retrieved from http://dx.doi.org/10.1016/8756-3282(96)00006-3
18.
GunterW. D.DalyK. (2012). Causal or spurious: Using propensity score matching to detangle the relationship between violent video games and violent behavior. Computers in Human Behavior, 28, 1348-1355. doi:10.1016/j.chb.2012.02.020
19.
GuoS.FraserM. W. (2009). Propensity score analysis: Statistical methods and applications. Thousand Oaks, CA: Sage.
20.
HavilandA.NaginD. S.RosenbaumP. R.TremblayR. E. (2008). Combining group-based trajectory modeling and propensity score matching for causal inferences in nonexperimental longitudinal data. Developmental psychology, 44, 422-436. doi:10.1037/0012-1649.44.2.422
21.
HernánM. A.LanoyE.CostagliolaD.RobinsJ. M. (2006). Comparison of dynamic treatment regimes via inverse probability weighting. Basic & Clinical Pharmacology & Toxicology, 98, 237-242. doi:10.1111/j.1742-7843.2006.pto_329.x
22.
HiscockR.BauldL.AmosA.FidlerJ. A.MunafòM. (2012). Socioeconomic status and smoking: A review. Annals of the New York Academy of Sciences, 1248(1), 107-123. doi:10.1111/j.1749-6632.2011.06202.x
23.
KalkwarfH. J.GilsanzV.LappeJ. M.OberfieldS.ShepherdJ. A.HangartnerT. N.ZemelB. S. (2010). Tracking of bone mass and density during childhood and adolescence. The Journal of Clinical Endocrinology & Metabolism, 95, 1690-1698. doi:10.1210/jc.2009-2319
24.
KeppelG.ZedeckS. (1989). Data analysis for research designs: analysis-of-variance and multiple regression, correlation approaches. New York, NY: W.H. Freeman Press.
25.
KilpatrickD. G.SaundersB. E. (1995). National Survey of Adolescents in the United States. Ann Arbor, MI: Inter-University Consortium for Political and Social Research.
26.
KovacsM.BarthR. P.LloydE. C.GreenR. L.JamesS.LeslieL. K.LandsverkJ. (2007). Children’s Depression Inventory. Predictors of placement moves among children with and without emotional and behavioral disorders, 15, 46-55.
27.
LeonA. C.HedekerD. (2007). Quintile stratification based on a misspecified propensity score in longitudinal treatment effectiveness analyses of ordinal doses. Computational Statistics & Data Analysis, 51, 6114-6122. doi:10.1016/j.csda.2006.12.021
LuncefordJ. K.DavidianM. (2004). Stratification and weighting via the propensity score in estimation of causal treatment effects: A comparative study. Statistics in Medicine, 23, 2937-2960. doi:10.1002/sim.1903
30.
LuntM.GlynnR. J.RothmanK. J.AvornJ.SturmerT. (2012). Propensity score calibration in the absence of surrogacy. American Journal of Epidemiology, 175, 1294-1302. doi:10.1093/aje/kwr463
31.
MatteiA. (2009). Estimating and using propensity score in presence of missing background data: An application to assess the impact of childbearing on well-being. Statistical Methods & Applications, 18, 257-273. doi:10.1007/s10260-007-0086-0
32.
McCaffreyD. F.RidgewayG.MorralA. R. (2004). Propensity score estimation with boosted regression for evaluating causal effects in observational studies. Psychological Methods, 9, 403-425. doi:10.1037/1082-989X.9.4.403.supp
33.
MonahanK. C.LeeJ. M.SteinbergL. (2011). Revisiting the impact of part-time work on adolescent adjustment: Distinguishing between selection and socialization using propensity score matching. Child Development, 82(1), 96-112. doi:10.1111/j.1467-8624.2010.01543.x
34.
PearlJ. (2009). Causality: Models, Reasoning, and Inference (2nd ed.). New York, NY: Cambridge University Press.
35.
QinR.TitlerM. G.SheverL. L.KimT. (2008). Estimating effects of nursing intervention via propensity score analysis. Nursing Research, 57, 444-452. doi:10.1097/NNR.0b013e31818c66f6
36.
QuY.LipkovichI. (2009). Propensity score estimation with missing values using a multiple imputation missingness pattern (MIMP) approach. Statistics in Medicine, 28, 1402-1414. doi:10.1002/sim.3549
37.
RogersR. G. (1991). Demographic characteristics of cigarette smokers in the United States. Social Biology, 38, (1-2), 1-12.
38.
RojewskiJ. W.LeeI. H.GemiciS. (2010). Using propensity score matching to determine the efficacy of secondary career academies in raising educational aspirations. Career and Technical Education Research, 35(1), 26.
39.
RosenbaumP. R. (1989). Optimal matching for observational studies. Journal of the American Statistical Association, 84, 1024-1032. doi:10.1080/01621459.1989.10478868
40.
RosenbaumP. R. (2002). Observational studies. (2nd ed.). New York: Springer-Verlag.
41.
RosenbaumP. R.RubinD. B. (1983). The central role of the propensity score in observational studies for causal effects. Biometrika, 70, 41-55. doi:10.1093/biomet/70.1.41
42.
RubinD. B. (1973). Matching to remove bias in observational studies. Biometrics, 29, 159-183. doi:10.2307/2529684
43.
RubinD. B. (2001). Using propensity scores to help design observational studies: Application to the tobacco litigation. Health Services and Outcomes Research Methodology, 2, 169-188. doi:10.1023/a:1020363010465
RyanR. M.JohnsonA.RigbyE.Brooks-GunnJ. (2011). The impact of childcare subsidy use on childcare quality. Early Childhood Research Quarterly, 26, 320-331. doi:10.1016/j.ecresq.2010.11.004
46.
SchaferJ. L.KangJ. (2008). Average causal effects from nonrandomized studies: A practical guide and simulated example. Psychological Methods, 13, 279-313. doi:10.1037/a0014268
47.
SegalJ. B.GriswoldM.Achy-BrouA. C.HerbertR.BassE. B.WuA. W.FrangakisC. E. (2007). Using propensity score subclassification to estimate effects of longitudinal treatments: An example using new diabetes medication. Medical Care, 45, 149-157.
48.
ShadishW. R.CookT. D.CampbellD. T. (2002). Experimental and quasi-experimental designs for generalized causal inference. Boston, MA: Houghton Mifflin Company.
49.
SpielbergerC. D. (1970). Preliminary manual for the State-trait Anxiety Inventory for children. Palo Alto, CA: Consulting Psychologist Press.
50.
StuartE. A. (2010). Matching methods for causal inference: A review and a look forward. Statistical Science, 25(1), 1-21. doi:10.1214/09-sts313
51.
StuartE. A.RubinD. B. (2008). Matching with multiple control groups with adjustment for group differences. Journal of Educational and Behavioral Statistics, 33, 279-306. doi:10.3102/1076998607306078
52.
StürmerT.SchneeweissS.AvornJ.GlynnR. J. (2005). Adjusting effect estimates for unmeasured confounding with validation data using propensity score calibration. American Journal of Epidemiology, 162, 279-289. doi:10.1093/aje/kwi192
53.
ThoemmesF. J. (2012). Propensity score matching in SPSS. Journal of Statistical Sciences. Accessed, November 26, 2013, http://arxiv.org/abs/1201.6385
54.
ThoemmesF. J.KimE. S. (2011). A systematic review of propensity score methods in the social sciences. Multivariate Behavioral Research, 46, 90-118. doi:10.1080/00273171.2011.540475
55.
WrightR.JohnL.EllenbogenS.OffordD. R.DukuE. K.RoweW. (2006). Effect of a structured arts program on the psychosocial functioning of youth from low-income communities: Findings from a Canadian longitudinal study. The Journal of Early Adolescence, 26, 186-205. doi:10.1177/0272431605285717
56.
ZanuttoE. L. (2006). A comparison of propensity score and linear regression analysis of complex survey data. Journal of Data Science, 4(1), 67-91.
57.
ZemelB. S.KalkwarfH. J.GilsanzV.LappeJ. M.OberfieldS.ShepherdJ. A.WinerK. K. (2011). Revised reference curves for bone mineral content and areal bone mineral density according to age and sex for black and nonblack children: Results of the bone mineral density in childhood study. The Journal of Clinical Endocrinology & Metabolism, 96, 3160-3169. doi:10.1210/jc.2011-1111
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
