The initial condition problem with complete history dependency in learning models for travel choices

Abstract: Learning-based models that capture travelers’ day-to-day learning processes in repeated travel choices could benefit from ubiquitous sensors such as smartphones, which provide individual-level longitudinal data to help validate and improve such models. However, the common problem of missing initial observations in longitudinal data collection can lead to inconsistent estimates of perceived value of attributes in question, and thus inconsistent parameter estimates. In this paper, the stated problem is addressed by treating the missing observations as latent variables. The proposed method is implemented in practice as maximum simulated likelihood (MSL) correction with two sampling methods in an instance-based learning model for travel choice, and the finite sample bias and efficiency of the estimators are investigated. Monte Carlo experimentation based on synthetic data shows that both the MSL with random sampling (MSLrs) and MSL with importance sampling (MSLis) are effective in correcting for the endogeneity problem in that the percent error and empirical coverage of the estimators are greatly improved after correction. Compared to the MSLrs method, the MSLis method is superior in both effectiveness and computational efficiency. Furthermore, MSLis passes a formal statistical test for the recovery of the population values up to a scale with a large number of missing observations, while MSLrs systematically fails due to the curse of dimensionality. The impacts of sampling size in MSLrs and number of high probability choice sequences in MSLis on the methods’ performances are investigated. The methods are applied to an experimental route-choice dataset to demonstrate their empirical application. Hausman-McFadden tests show that the estimators after correction are statistically equal to the estimators of the full dataset without missing observations, confirming that the proposed methods are practical and effective for addressing the stated problem.

[1]  Moshe Ben-Akiva,et al.  Sampling of alternatives in Logit Mixture models , 2013 .

[2]  Jeffrey M. Wooldridge,et al.  The Initial Conditions Problem in Dynamic, Nonlinear Panel Data Models with Unobserved Heterogeneity , 2002 .

[3]  Lung-fei Lee,et al.  Simulated Maximum Likelihood Estimation of Dynamic Discrete Choice Statistical Models Some Monte Carlo Results , 1997 .

[4]  Bo E. Honoré,et al.  Panel Data Discrete Choice Models with Lagged Dependent Variables , 2000 .

[5]  Nicole A. Lazar,et al.  Statistical Analysis With Missing Data , 2003, Technometrics.

[6]  Moshe Ben-Akiva,et al.  Sampling of alternatives in Multivariate Extreme Value (MEV) models , 2013 .

[7]  C. A. Guevara,et al.  Correcting for endogeneity due to omitted attributes in discrete-choice models: the multiple indicator solution , 2016 .

[8]  R. Blundell,et al.  Initial Conditions and Moment Restrictions in Dynamic Panel Data Models , 1998 .

[9]  C. Lebiere,et al.  Instance-Based Cognitive Models of Decision-Making , 2005 .

[10]  J. Heckman.  Dummy Endogenous Variables in a Simultaneous Equation System , 1977 .

[11]  John R. Anderson,et al.  Reflections of the Environment in Memory Form of the Memory Functions , 2022 .

[12]  Allen and Rosenbloom Paul S. Newell,et al.  Mechanisms of Skill Acquisition and the Law of Practice , 1993 .

[13]  C. Angelo Guevara,et al.  Critical assessment of five methods to correct for endogeneity in discrete-choice models , 2015 .

[14]  K. Train,et al.  A Control Function Approach to Endogeneity in Consumer Choice Models , 2010 .

[15]  D. McFadden,et al.  MIXED MNL MODELS FOR DISCRETE RESPONSE , 2000 .

[16]  Cristian Angelo Guevara,et al.  A Monte Carlo experiment to analyze the curse of dimensionality in estimating random coefficients models with a full variance-covariance matrix , 2012 .

[17]  Rob J Hyndman,et al.  Estimating and Visualizing Conditional Densities , 1996 .

[18]  Bo E. Honoré,et al.  Bounds on Parameters in Panel Dynamic Discrete Choice Models , 2006 .

[19]  Song Gao,et al.  Travelers' Day-to-Day Route Choice Behavior with Real-Time Information in a Congested Risky Network , 2014 .

[20]  Joseph Plasmans,et al.  Policymakers’ Coalitions and Stabilization Policies in the EMU , 2004 .

[21]  D. Brownstone.  Multiple Imputations for LInear Regression Models , 1991 .

[22]  Steven T. Berry,et al.  Automobile Prices in Market Equilibrium , 1995 .

[23]  Nathaniel Schenker,et al.  Asymptotic results for multiple imputation , 1988 .

[24]  Cristian Angelo Guevara,et al.  Change of Scale and Forecasting with the Control-Function Method in Logit Models , 2011, Transp. Sci..

[25]  Cristián Angelo Guevara-Cue.  Endogeneity and Sampling of Alternatives in Spatial Choice Models , 2010 .

[26]  D. McFadden,et al.  Specification tests for the multinomial logit model , 1984 .

[27]  Jesus M. Carro.  Estimating Dynamic Panel Data Discrete Choice Models with Fixed Effects , 2003 .

[28]  Cleotilde Gonzalez,et al.  Instance-based learning in dynamic decision making , 2003, Cogn. Sci..

[29]  D. Rubin,et al.  One Hundred Years of Forgetting : A Quantitative Description of Retention , 1996 .

[30]  Eran Ben-Elia,et al.  Which road do I take? A learning-based model of route-choice behavior with real-time information , 2010 .

[31]  M. Bierlaire,et al.  Correcting for endogeneity due to omitted attitudes: Empirical assessment of a modified MIS method using RP mode choice data , 2016 .

[32]  Song Gao,et al.  An exploratory study of instance-based learning for route choice with random travel times , 2017 .

[33]  Florian Heiss,et al.  Discrete Choice Methods with Simulation , 2016 .