Hybridizing Machine Learning Methods and Finite Mixture Models for Estimating Heterogeneous Treatment Effects in Latent Classes

Abstract

There has been increasing interest in exploring heterogeneous treatment effects using machine learning (ML) methods such as causal forests, Bayesian additive regression trees, and targeted maximum likelihood estimation. However, there is little work on applying these methods to estimate treatment effects in latent classes defined by well-established finite mixture/latent class models. This article proposes a hybrid method, a combination of finite mixture modeling and ML methods from causal inference to discover effect heterogeneity in latent classes. Our simulation study reveals that hybrid ML methods produced more precise and accurate estimates of treatment effects in latent classes. We also use hybrid ML methods to estimate the differential effects of private lessons across latent classes from Trends in International Mathematics and Science Study data.

Keywords

causal inference machine learning methods observational studies multilevel propensity score matching finite mixture modeling

Get full access to this article

View all access options for this article.

References

Allman

E. S.

Matias

Rhodes

J. A.

(2009). Identifiability of parameters in latent structure models with many observed variables. The Annals of Statistics, 37(6A), 3099–3132.

Athey

Imbens

(2016). Recursive partitioning for heterogeneous causal effects. Proceedings of the National Academy of Sciences, 113(27), 7353–7360.

Athey

Tibshirani

Wager

(2019). Generalized random forests. The Annals of Statistics, 47(2), 1148–1178.

Austin

P. C.

(2011). An introduction to propensity score methods for reducing the effects of confounding in observational studies. Multivariate Behavioral Research, 46, 399–424.

Bakk

Tekle

F. B.

Vermunt

J. K.

(2013). Estimating the association between latent class membership and external variables using bias-adjusted three-step approaches. Sociological Methodology, 43(1), 272–311.

Bandura

(2010). Self-efficacy. In Weiner

I. B.

Craighead

W. E.

(Eds.), The corsini encyclopedia of psychology (4th ed., pp. 1–3). Hoboken, NJ: Wiley.

Breiman

(2001). Random forests. Machine Learning, 45(1), 5–32.

Butera

N. M.

Lanza

S. T.

Coffman

D. L.

(2014). A framework for estimating causal effects in latent class analysis: Is there a causal link between early sex and subsequent profiles of delinquency? Prevention Science, 15(3), 397–407.

Clogg

C. C.

(1995). Latent class models. In Sobel

M. E.

Arminger

Clogg

C. C.

(Eds.), Handbook of statistical modeling for the social and behavioral sciences (pp. 311–359). Springer.

10.

Dempster

A. P.

Laird

N. M.

Rubin

D. B.

(1977). Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society: Series B (Methodological), 39(1), 1–22.

11.

Dorie

Hill

(2019). bartcause: Causal inference using Bayesian additive regression trees [Computer software manual] (R package version 1.0-0). https://github.com/vdorie/bartCause

12.

Everitt

B. S.

Hand

D. J.

(1981). Finite mixture distributions. Chapman and Hall.

13.

Foy

Arora

Stanco

(2017). TIMSS 2015 user guide for the international database. TIMSS & PIRLS International Study Center, Boston College.

14.

Goodman

L. A.

(2007). On the assignment of individuals to latent classes. Sociological Methodology, 37(1), 1–22.

15.

Gruber

van der Laan

M. J.

(2012). tmle: An R package for targeted maximum likelihood estimation. Journal of Statistical Software, 51(13), 1–35. http://www.jstatsoft.org/v51/i13/ (doi:10.18637/jss.v051.i13)

16.

Grün

Leisch

(2008). Identifiability of finite mixtures of multinomial logit models with varying and fixed effects. Journal of Classification, 25(2), 225–247.

17.

Hallquist

Wiley

(2017). MplusAutomation: Automating Mplus model estimation and interpretation [Computer software manual] (R package version 0.7). https://CRAN.R-project.org/package=MplusAutomation

18.

Hill

J. L.

(2011). Bayesian nonparametric modeling for causal inference. Journal of Computational and Graphical Statistics, 20(1), 217–240.

19.

Hong

(2009). Reading instruction time and homogeneous grouping in kindergarten: An application of marginal mean weighting through stratification. Educational Evaluation and Policy Analysis, 31(1), 54–81.

20.

Hong

Raudenbush

S. W.

(2006). Evaluating kindergarten retention policy: A case study of causal inference for multilevel observational data. Journal of the American Statistical Association, 101(475), 901–910.

21.

Imai

Ratkovic

(2013). Estimating treatment effect heterogeneity in randomized program evaluation. The Annals of Applied Statistics, 7(1), 443–470.

22.

Imbens

G. W.

Rubin

D. B.

(2015). Causal inference in statistics, social, and biomedical sciences. Cambridge University Press.

23.

Wang

C.-P.

Ialongo

N. S.

(2009). Using latent outcome trajectory classes in causal inference. Statistics and its Interface, 2(4), 403.

24.

Kang

Schafer

J. L.

(2010). Estimating average treatment effects when the treatment is a latent class (Technical Report No. 10-05). Department of Statistics, The Pennsylvania State University.

25.

Kaplan

Kim

J.-S.

Kim

S.-Y.

(2009). Multilevel latent variable modeling: Current research and recent developments. In Millsap

R. E.

Maydeu-Olivares

(Eds.), Handbook of quantitative methods in psychology (pp. 592–612). Sage.

26.

Kim

J.-S.

Steiner

P. M.

(2015). Multilevel propensity score methods for estimating causal effects: A latent class modeling strategy. In van der Ark

Bolt

Wang

W.-C.

Douglas

Wiberg

(Eds.), Quantitative psychology research: The 80th annual meeting of the psychometric society (pp. 293–306). Springer.

27.

Kim

J.-S.

Steiner

P. M.

Lim

W. C.

(2016). Mixture modeling methods for causal inference with multilevel data. In Harring

J. R.

Stapleton

L. M.

Beretvas

S. N.

(Eds.), Advances in multilevel modeling for educational research (pp. 335–359). Information Age Publishing.

28.

Künzel

S. R.

Sekhon

J. S.

Bickel

P. J.

(2019). Metalearners for estimating heterogeneous treatment effects using machine learning. Proceedings of the National Academy of Sciences, 116(10), 4156–4165.

29.

Lanza

S. T.

Coffman

D. L.

(2013). Causal inference in latent class analysis. Structural Equation Modeling: A Multidisciplinary Journal, 20(3), 361–383.

30.

Leisch

(2004). Flexmix: A general framework for finite mixture models and latent glass regression in R. Journal of Statistical Software, 11, 1–18.

31.

Leite

(2016). Practical propensity score methods using R. Sage.

32.

Lenk

P. J.

DeSarbo

W. S.

(2000). Bayesian inference for finite mixtures of generalized linear models with random effects. Psychometrika, 65(1), 93–119.

33.

(2018). Using classification and regression trees: A practical primer. Information Age Publishing.

34.

Magidson

Vermunt

J. K.

(2004). Latent class models. In Kaplan

(Ed.), The Sage handbook of quantitative methodology for the social sciences (pp. 175–198). Sage.

35.

Martin

M. O.

Mullis

I. V. S.

Hooper

(2016). Methods and procedures in TIMSS 2015. TIMSS & PIRLS International Study Center, Boston College. http://timssandpirls.bc.edu/publications/timss/2015-methods.html

36.

Masyn

K. E.

(2013). Latent class analysis and finite mixture modeling. In Little

(Ed.), The Oxford handbook of quantitative methods (pp. 551–611). Oxford University Press.

37.

McLachlan

G. J.

Peel

(2000). Finite mixture models. Wiley.

38.

Mok

J.-Y.

Choi

S.-W.

Kcim

D.-J.

Choi

J.-S.

Lee

Ahn

Eun-Jeung

Song

W.-Y.

(2014). Latent class analysis on Internet and smartphone addiction in college students. Neuropsychiatric Disease and Treatment, 10, 817.

39.

Muthén

B. O.

(2017). Mplus user’s guide (8th ed.). Los Angeles, CA: Muthén & Muthén.

40.

Neyman

J. S.

(1923). On the application of probability theory to agricultural experiments: Essay on principles. section 9 (with discussion). Statistical Science, 4, 465–480.

41.

R Core Team. (2019). R: A language and environment for statistical computing [Computer software manual]. https://www.R-project.org/

42.

Rosenbaum

P. R.

Rubin

D. B.

(1983). The central role of the propensity score in observational studies for causal effects. Biometrika, 70, 41–55.

43.

Rubin

D. B.

(1974). Estimating causal effects of treatments in randomized and nonrandomized studies. Journal of Educational Psychology, 66(5), 688–701.

44.

Rubin

D. B.

(1986). Comment: Which is have causal answers. Journal of the American Statistical Association, 81(396), 961–962.

45.

Rutkowski

Gonzalez

Joncas

von Davier

(2010). International large-scale assessment data: Issues in secondary analysis and reporting. Educational Researcher, 39(2), 142–151.

46.

Schafer

J. L.

Kang

(2008). Average causal effects from nonrandomized studies: A practical guide and simulated example. Psychological Methods, 13(4), 279.

47.

Schuler

M. S.

Leoutsakos

J.-M. S.

Stuart

E. A.

(2014). Addressing confounding when estimating the effects of latent classes on a distal outcome. Health Services and Outcomes Research Methodology, 14(4), 232–254.

48.

Steiner

P. M.

Cook

(2013). Matching and propensity scores. In Little

(Ed.), The Oxford handbook of quantitative methods (pp. 236–258). Oxford University Press.

49.

Stephens

(2000). Dealing with label switching in mixture models. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 62(4), 795–809.

50.

Tsai

C.-L.

Wang

Nickerson

D. M.

(2009). Subgroup analysis via recursive partitioning. Journal of Machine Learning Research, 10(5), 141–158.

51.

Suk

Kang

Kim

J.-S.

(2019, September). Random forests approach for causal inference with clustered observational data. PsyArXiv. psyarxiv.com/xgq2k

52.

Sutfin

E. L.

Reboussin

B. A.

McCoy

T. P.

Wolfson

(2009). Are college student smokers really a homogeneous group? A latent class analysis of college student smokers. Nicotine & Tobacco Research, 11(4), 444–454.

53.

Tibshirani

Athey

Friedberg

Hadad

Miner

Wager

Wright

(2019). grf: Generalized random forests (beta) [Computer software manual] (R package version 0.10.3). https://CRAN.R-project.org/package=grf

54.

Titterington

D. M.

Smith

A. F. M.

Makov

U. E.

(1985). Statistical analysis of finite mixture distributions. Wiley.

55.

Tueller

S. J.

Drotar

Lubke

G. H.

(2011). Addressing the problem of switched class labels in latent variable mixture model simulation studies. Structural Equation Modeling, 18(1), 110–131.

56.

van der Laan

M. J.

Polley

E. C.

Hubbard

A. E.

(2007). Super learner. Statistical Applications in Genetics and Molecular Biology, 6(1), Article 25.

57.

van der Laan

M. J.

Rubin

(2006). Targeted maximum likelihood learning. The International Journal of Biostatistics, 2(1), 1–40.

58.

Vermunt

J. K.

(2003). Multilevel latent class models. Sociological Methodology, 33(1), 213–239.

59.

Vermunt

J. K.

(2010). Latent class modeling with covariates: Two improved three-step approaches. Political Analysis, 18(4), 450–469.

60.

Vermunt

J. K.

Magidson

(2003). Latent class models for classification. Computational Statistics & Data Analysis, 41(3-4), 531–537.

61.

Wager

Athey

(2018). Estimation and inference of heterogeneous treatment effects using random forests. Journal of the American Statistical Association, 113(523), 1228–1242.

62.

Wang

(2012). Structural equation modeling: Applications using Mplus. John Wiley & Sons.

63.

Wang

M. C.

Gordon

E. W.

(2012). Educational resilience in inner-city America: Challenges and prospects. Routledge.

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.

0.00 MB

5.44 MB