×

zbMATH — the first resource for mathematics

Estimating peer effects in longitudinal dyadic data using instrumental variables. (English) Zbl 1299.92029
Summary: The identification of causal peer effects (also known as social contagion or induction) from observational data in social networks is challenged by two distinct sources of bias: latent homophily and unobserved confounding. In this paper, we investigate how causal peer effects of traits and behaviors can be identified using genes (or other structurally isomorphic variables) as instrumental variables (IV) in a large set of data generating models with homophily and confounding. We use directed acyclic graphs to represent these models and employ multiple IV strategies and report three main identification results. First, using a single fixed gene (or allele) as an IV will generally fail to identify peer effects if the gene affects past values of the treatment. Second, multiple fixed genes/alleles, or, more promisingly, time-varying gene expression, can identify peer effects if we instrument exclusion violations as well as the focal treatment. Third, we show that IV identification of peer effects remains possible even under multiple complications often regarded as lethal for IV identification of intra-individual effects, such as pleiotropy on observables and unobservables, homophily on past phenotype, past and ongoing homophily on genotype, inter-phenotype peer effects, population stratification, gene expression that is endogenous to past phenotype and past gene expression, and others. We apply our identification results to estimating peer effects of body mass index (BMI) among friends and spouses in the Framingham Heart Study. Results suggest a positive causal peer effect of BMI between friends.
MSC:
92C50 Medical applications (general)
62P10 Applications of statistics to biology and medical sciences; meta analysis
91D30 Social networks; opinion dynamics
PDF BibTeX XML Cite
Full Text: DOI
References:
[1] Angrist, Identification of causal effects using instrumental variables, Journal of the American Statistical Association 91 pp 444– (1996) · Zbl 0897.62130 · doi:10.1080/01621459.1996.10476902
[2] Brito, Instrument sets, Heuristics, Probability and Causality: A Tribute to Judea Pearl pp 295– (2010)
[3] Brito, A new identification condition for recursive models with correlated errors, Structural Equation Modeling 9 pp 459– (2002) · doi:10.1207/S15328007SEM0904_1
[4] Carrell, Does your cohort matter? Estimating peer effects in college achievement, Journal of Labor Economics 27 pp 439– (2009) · doi:10.1086/600143
[5] Centola, The spread of behavior in an online social network, Science 329 pp 1194– (2010) · doi:10.1126/science.1185231
[6] Christakis, The spread of obesity in a large social network over 32 years, New England Journal of Medicine 357 pp 370– (2007) · doi:10.1056/NEJMsa066082
[7] Christakis, Dynamics of smoking behavior in a large social network, New England Journal of Medicine 358 pp 2249– (2008) · doi:10.1056/NEJMsa0706154
[8] Didelez, Mendelian randomization as an instrumental variable approach to causal inference, Statistical Methods for Medical Research 16 pp 309– (2007) · Zbl 1122.62343 · doi:10.1177/0962280206077743
[9] Didelez, Assumptions of IV methods for observational epidemiology, Statistical Science 25 pp 22– (2010) · Zbl 1328.62587 · doi:10.1214/09-STS316
[10] Elwert, Graphical causal models, Handbook of Causal Analysis for Social Research pp 245– (2013) · doi:10.1007/978-94-007-6094-3_13
[11] Elwert, Wives and ex-wives: A new test for homogamy bias in the widowhood effect, Demography 45 pp 851– (2008) · doi:10.1353/dem.0.0029
[12] Fletcher, Social interactions and smoking: Evidence using multiple student cohorts, instrumental variables, and school fixed effects, Health Economics 19 pp 466– (2008) · doi:10.1002/hec.1488
[13] Fowler, Cooperative behavior cascades in human social networks, PNAS: Proceedings of the National Academy of Sciences 107 pp 5334– (2010) · doi:10.1073/pnas.0913149107
[14] Hernán, Instruments for causal inference-An epidemiologist’s dream?, Epidemiology 17 pp 360– (2006) · doi:10.1097/01.ede.0000222409.00878.37
[15] Lasky-Su, On the replication of genetic associations: Timing can be everything, The American Journal of Human Genetics 82 pp 849– (2008) · doi:10.1016/j.ajhg.2008.01.018
[16] O’Malley, Longitudinal analysis of large social networks: Estimating the effect of health traits on changes in friendship ties, Statistics in Medicine 30 pp 950– (2011) · doi:10.1002/sim.4190
[17] Palmer, Using multiple genetic variants as instrumental variables for modifiable risk factors, The International Journal of Biostatistics 21 pp 223– (2012)
[18] Pearl, Probabilistic Reasoning in Intelligent Systems (1988) · Zbl 0746.68089
[19] Pearl, Causal diagrams for empirical research, Biometrika 82 pp 669– (1995) · Zbl 0860.62045 · doi:10.1093/biomet/82.4.669
[20] Pearl, Causality (2009) · doi:10.1017/CBO9780511803161
[21] Price, Principal components analysis corrects for stratification in genome-wide association studies, Nature Genetics 38 pp 904– (2006) · doi:10.1038/ng1847
[22] Richardson, Single world intervention graphs (swigs): A unification of the counterfactual and graphical approaches to causality, Center for Statistics and the Social Sciences, University of Washington (2013)
[23] Rosenquist, The spread of alcohol consumption behavior in a large social network, Annals of Internal Medicine 152 pp 426– (2010) · doi:10.7326/0003-4819-152-7-201004060-00007
[24] Sacerdote, Peer effects with random assignment: results for Dartmouth roommates, Quarterly Journal of Economics 116 pp 681– (2001) · Zbl 0996.91553 · doi:10.1162/00335530151144131
[25] Shalizi, Homophily and contagion are generically confounded in observational social network studies, Sociological Methods and Research 40 pp 211– (2011) · doi:10.1177/0049124111404820
[26] Speliotes, Association analyses of 249,796 individuals reveal 18 new loci associated with body mass index, Nature Genetics 42 pp 937– (2010) · doi:10.1038/ng.686
[27] Stock, A survey of weak instruments and weak identification in generalized method of moments, Journal of Business and Economics Statistics 20 pp 518– (2002) · doi:10.1198/073500102288618658
[28] VanderWeele, Why and when flawed social network analyses still yield valid tests of no contagion, Statistics, Politics, and Policy 3 (2012) · doi:10.1515/2151-7509.1050
[29] Vansteelandt, On instrumental variables estimation of causal odds ratios, Statistical Science 26 pp 403– (2011) · Zbl 1246.62224 · doi:10.1214/11-STS360
[30] Verma, Causal networks: Semantics and expressiveness, Proceedings of the Fourth Workshop on Uncertainty in Artificial Intelligence pp 352– (1988)
[31] White, Instrumental variables regression with independent observations, Econometrica 50 pp 483– (1982) · Zbl 0518.62094 · doi:10.2307/1912639
[32] Wing, Benefits of recruiting participants with friends and increasing social support for weight loss and maintenance, Journal of Consulting and Clinical Psychology 67 pp 132– (1999) · doi:10.1037/0022-006X.67.1.132
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.