A Causal Latent Transition Model With Multivariate Outcomes and Unobserved Heterogeneity: Application to Human Capital Development

In order to evaluate the effect of a policy or treatment with pre- and post-treatment outcomes, we propose an approach based on a transition model, which may be applied with multivariate outcomes and accounts for unobserved heterogeneity. This model is based on potential versions of discrete latent variables representing the individual characteristic of interest and may be cast in the hidden (latent) Markov literature for panel data. Therefore, it can be estimated by maximum likelihood in a relatively simple way. The approach extends the difference-in-difference method as it is possible to deal with multivariate outcomes. Moreover, causal effects may be expressed with respect to transition probabilities. The proposal is validated through a simulation study, and it is applied to evaluate educational programs administered to pupils in the sixth and seventh grades during their middle school period. These programs are carried out in an Italian region to improve non-cognitive skills (CSs). We study if they impact also on students’ CSs in Italian and Mathematics in the eighth grade, exploiting the pretreatment test scores available in the fifth grade. The main conclusion is that the educational programs aimed to develop noncognitive abilities help the best students to maintain their higher cognitive abilities over time.

[1]  Per-Anders Edin,et al.  The Rising Return to Noncognitive Skill , 2022, American Economic Journal: Applied Economics.

[2]  F. Bartolucci,et al.  Discrete Latent Variable Models , 2021, Annual Review of Statistics and Its Application.

[3]  C. E. Schultz.  Fulvia , 2021 .

[4]  Seung Jun Shin,et al.  Model-Based Clustering and Classification for Data Science: With Applications in R , 2020, The American Statistician.

[5]  Paul R. Rosenbaum,et al.  Modern Algorithms for Matching in Observational Studies , 2020, Annual Review of Statistics and Its Application.

[6]  A. Raftery,et al.  Model-Based Clustering and Classification for Data Science , 2019 .

[7]  Pedro H. C. Sant'Anna,et al.  Doubly Robust Difference-in-Differences Estimators , 2018, Journal of Econometrics.

[8]  Christian P. Robert,et al.  Handbook of Mixture Analysis , 2018 .

[9]  Francesco Bartolucci,et al.  Lmest: An R package for latent Markov models for longitudinal categorical data , 2017 .

[10]  Per-Anders Edin,et al.  The Rising Return to Non-Cognitive Skill , 2017, SSRN Electronic Journal.

[11]  J. García-Pérez,et al.  No student left behind? Evidence from the Programme for School Guidance in Spain , 2016 .

[12]  Myoung-jae Lee,et al.  Matching, Regression Discontinuity, Difference in Differences, and Beyond , 2016 .

[13]  Francesco Bartolucci,et al.  Causal Latent Markov Model for the Comparison of Multiple Treatments in Observational Longitudinal Studies , 2016 .

[14]  Rebecca E. Martin,et al.  Promise and Paradox : Measuring Students ’ Non-Cognitive Skills and the Impact of Schooling , 2015 .

[15]  Iain L. MacDonald,et al.  Hidden Markov Models for Discrete-Valued Time Series , 2015 .

[16]  A. Farcomeni,et al.  Latent Markov models: a review of a general framework for the analysis of longitudinal data with covariates , 2014, TEST.

[17]  Francesco Bartolucci,et al.  Latent Markov models: a review of a general framework for the analysis of longitudinal data with covariates , 2014 .

[18]  Olmo Silva,et al.  Targeting Noncognitive Skills to Improve Cognitive Outcomes: Evidence from a Remedial Education Intervention , 2014, Journal of Human Capital.

[19]  Stephanie T. Lanza,et al.  Causal Inference in Latent Class Analysis , 2013, Structural equation modeling : a multidisciplinary journal.

[20]  David Isaacs,et al.  Making a difference , 2013, Journal of paediatrics and child health.

[21]  Silvia Pandolfi,et al.  A comparison of some criteria for states selection in the latent Markov model for longitudinal data , 2012, Adv. Data Anal. Classif..

[22]  Francesco Bartolucci,et al.  Latent Markov Models for Longitudinal Data , 2012 .

[23]  J. Heckman,et al.  Hard Evidence on Soft Skills , 2012, Labour economics.

[24]  M. Lechner.  The Estimation of Causal Effects by Difference-in-Difference Methods , 2011 .

[25]  Pedro S. Martins.  Can Targeted, Non-Cognitive Skills Programs Improve Achievement? Evidence from Epis , 2010 .

[26]  Franco Peracchi,et al.  Regression with Imputed Covariates: A Generalized Missing Indicator Approach , 2009 .

[27]  Francesco Bartolucci,et al.  Assessment of School Performance Through a Multilevel Latent Markov Rasch Model , 2009, 0909.4961.

[28]  James J. Heckman,et al.  Estimating the Technology of Cognitive and Noncognitive Skill Formation , 2010, Econometrica : journal of the Econometric Society.

[29]  E. Deci,et al.  Self‐determination theory and work motivation , 2005 .

[30]  James J. Heckman,et al.  Interpreting the Evidence on Life Cycle Skill Formation , 2005, SSRN Electronic Journal.

[31]  Kathleen J. Mullen,et al.  The Effect of Schooling and Ability on Achievement Test Scores , 2003 .

[32]  Geoffrey J. McLachlan,et al.  Finite Mixture Models , 2019, Annual Review of Statistics and Its Application.

[33]  Joseph Kahne,et al.  The Role of Social Capital in Youth Development: The Case of “I Have a Dream” Programs , 1999 .

[34]  Petra E. Todd,et al.  Matching As An Econometric Evaluation Estimator: Evidence from Evaluating a Job Training Programme , 1997 .

[35]  M. Keane,et al.  The Career Decisions of Young Men , 1997, Journal of Political Economy.

[36]  Joseph P. Tierney.  Making a Difference. An Impact Study of Big Brothers/Big Sisters. , 1995 .

[37]  G. Vittadini.  Indeterminacy Problems in the Lisrel Model. , 1989, Multivariate behavioral research.

[38]  D. Rubin,et al.  The central role of the propensity score in observational studies for causal effects , 1983 .

[39]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[40]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[41]  H. Weisberg,et al.  Value-Added Analysis: A Dynamic Approach to the Estimation of Treatment Effects , 1976 .

[42]  L. Baum,et al.  A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains , 1970 .

[43]  K. Jöreskog.  Testing a simple structure hypothesis in factor analysis , 1966, Psychometrika.

[44]  Angela L. Duckworth,et al.  Promise and Paradox: Measuring Students’ Non-cognitive Skills and the Impact of Schooling , 2014 .

[45]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[46]  James J. Heckman,et al.  The myth of achievement tests : the GED and the role of character in American life , 2013 .

[47]  Susanne M. Schennach,et al.  Web Appendix for \Estimating the Technology of Cognitive and Noncognitive Skill Formation" , 2010 .

[48]  Patrick A. Puhani.  The Treatment Effect , the Cross Difference , and the Interaction Term in Nonlinear “ Difference-in-Differences ” Models , 2008 .

[49]  Alberto Abadie.  Semiparametric Difference-in-Differences Estimators , 2005 .

[50]  S. Srivastava,et al.  The Big Five Trait taxonomy: History, measurement, and theoretical perspectives. , 1999 .

[51]  G. Becker,et al.  Human Capital: A Theoretical and Empirical Analysis with Special Reference to Education, Third Edition , 1993 .