Modeling Dynamic Preferences: A Bayesian Robust Dynamic Latent Ordered Probit Model

Much politico-economic research on individuals’ preferences is cross-sectional and does not model dynamic aspects of preference or attitude formation. I present a Bayesian dynamic panel model, which facilitates the analysis of repeated preferences using individual-level panel data. My model deals with three problems. First, I explicitly include feedback from previous preferences taking into account that available survey measures of preferences are categorical. Second, I model individuals' initial conditions when entering the panel as resulting from observed and unobserved individual attributes. Third, I capture unobserved individual preference heterogeneity both via standard parametric random effects and a robust alternative based on Bayesian nonparametric density estimation. I use this model to analyze the impact of income and wealth on preferences for government intervention using the British Household Panel Study from 1991 to 2007.

[1]  Diane Lambert,et al.  Generalizing Logistic Regression by Nonparametric Mixing , 1989 .

[2]  Jeffrey M. Woodbridge.  Econometric Analysis of Cross Section and Panel Data , 2002 .

[3]  H. Ishwaran,et al.  Markov chain Monte Carlo in approximate Dirichlet and beta two-parameter process hierarchical models , 2000 .

[4]  Yotam Margalit.  Explaining Social Policy Preferences: Evidence from the Great Recession , 2013, American Political Science Review.

[5]  J. Gill.  Is Partial-Dimension Convergence a Problem for Inferences from MCMC Algorithms? , 2007, Political Analysis.

[6]  D. Rubin,et al.  Inference from Iterative Simulation Using Multiple Sequences , 1992 .

[7]  Michael Escobar,et al.  Nonparametric Bayesian methods in hierarchical models , 1995 .

[8]  Gareth O. Roberts,et al.  Convergence assessment techniques for Markov chain Monte Carlo , 1998, Stat. Comput..

[9]  Fernando A. Quintana,et al.  Nonparametric Bayesian data analysis , 2004 .

[10]  Aldi J. M. Hagenaars,et al.  Poverty Statistics in the Late 1980s: Research Based on Micro-data , 1994 .

[11]  C. Antoniak.  Mixtures of Dirichlet Processes with Applications to Bayesian Nonparametric Problems , 1974 .

[12]  Justin Grimmer.  An Introduction to Bayesian Inference via Variational Approximations , 2011, Political Analysis.

[13]  D. Stegmueller,et al.  Apples and Oranges? The Problem of Equivalence in Comparative Research , 2011, Political Analysis.

[14]  Claudia Czado,et al.  Modeling individual migraine severity with autoregressive ordered probit models , 2011, Stat. Methods Appl..

[15]  Philipp Rehm.  Risk Inequality and the Polarized American Electorate , 2010, British Journal of Political Science.

[16]  N. Laird.  Nonparametric Maximum Likelihood Estimation of a Mixing Distribution , 1978 .

[17]  H. Ishwaran,et al.  Exact and approximate sum representations for the Dirichlet process , 2002 .

[18]  A. Alesina,et al.  Preferences for Redistribution in the Land of Opportunities , 2001 .

[19]  Corwin D. Smidt,et al.  The dynamic properties of individual-level party identification in the United States , 2011 .

[20]  J. Heckman,et al.  A Method for Minimizing the Impact of Distributional Assumptions in Econometric Models for Duration Data , 1984 .

[21]  S. Chib,et al.  Bayesian analysis of binary and polychotomous response data , 1993 .

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

[23]  Thomas R. Cusack,et al.  Risks at Work: The Demand and Supply Sides of Government Redistribution , 2005 .

[24]  Wiji Arulampalam,et al.  Simplified Implementation of the Heckman Estimator of the Dynamic Probit Model and a Comparison with Alternative Estimators , 2007, SSRN Electronic Journal.

[25]  Nathaniel Beck,et al.  Nuisance vs. Substance: Specifying and Estimating Time-Series-Cross-Section Models , 1996, Political Analysis.

[26]  M. Schlesinger,et al.  Insecure Alliances: Risk, Inequality, and Support for the Welfare State , 2012, American Political Science Review.

[27]  Arthur Spirling,et al.  Identifying Intraparty Voting Blocs in the U.K. House of Commons , 2010 .

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

[29]  M. Arellano,et al.  Some Tests of Specification for Panel Data: Monte Carlo Evidence and an Application to Employment Equations , 1991 .

[30]  Ying Lu,et al.  Bayesian and Likelihood Inference for 2 × 2 Ecological Tables: An Incomplete-Data Approach , 2007, Political Analysis.

[31]  M. Wallerstein,et al.  Inequality, Social Insurance, and Redistribution , 2001, American Political Science Review.

[32]  On the number of categories in an ordered regression model , 2002 .

[33]  T. Griffiths,et al.  Modeling individual differences using Dirichlet processes , 2006 .

[34]  T. Iversen,et al.  "Economic Shocks, Inequality and Popular Support for Redistribution" , 2008 .

[35]  Cheng Hsiao,et al.  Estimation of Dynamic Models with Error Components , 1981 .

[36]  C. Varin,et al.  A mixed autoregressive probit model for ordinal longitudinal data. , 2010, Biostatistics.

[37]  A. Gelman.  Prior distributions for variance parameters in hierarchical models (comment on article by Browne and Draper) , 2004 .

[38]  George Casella,et al.  Sampling schemes for generalized linear Dirichlet process random effects models , 2011, Stat. Methods Appl..

[39]  Claudia Czado,et al.  An Autoregressive Ordered Probit Model With Application to High-Frequency Financial Data , 2005 .

[40]  S. Chib,et al.  Bayesian residual analysis for binary response regression models , 1995 .

[41]  Jeroen K. Vermunt,et al.  An EM algorithm for the estimation of parametric and nonparametric hierarchical nonlinear models , 2004 .

[42]  Christopher Wlezien.  The Public as Thermostat: Dynamics of Preferences for Spending , 1995 .

[43]  Alpaslan Akay,et al.  Finite‐sample comparison of alternative methods for estimating dynamic panel data models , 2012 .

[44]  R. McKelvey,et al.  A statistical model for the analysis of ordinal level dependent variables , 1975 .

[45]  M. Escobar,et al.  Markov Chain Sampling Methods for Dirichlet Process Mixture Models , 2000 .

[46]  P. Müller,et al.  Semiparametric Bayesian Inference for Multilevel Repeated Measurement Data , 2007, Biometrics.

[47]  Adam J. Branscum,et al.  Bayesian Nonparametric Modeling and Data Analysis: An Introduction , 2005 .

[48]  N. Pillai,et al.  Bayesian density regression , 2007 .

[49]  Hairul Azlan Annuar,et al.  Foreign investors' interests and corporate tax avoidance: Evidence from an emerging economy , 2015 .

[50]  Michael,et al.  On a Class of Bayesian Nonparametric Estimates : I . Density Estimates , 2008 .

[51]  Simon Jackman,et al.  Estimation and Inference Are Missing Data Problems: Unifying Social Science Statistics via Bayesian Simulation , 2000, Political Analysis.

[52]  Xun Pang,et al.  Modeling Heterogeneity and Serial Correlation in Binary Time-Series Cross-sectional Data: A Bayesian Multilevel Model with AR(p) Errors , 2010, Political Analysis.

[53]  P. Müller,et al.  Nonparametric Bayesian Modeling for Multivariate Ordinal Data , 2005 .

[54]  Y. Mundlak.  On the Pooling of Time Series and Cross Section Data , 1978 .

[55]  A. Gelman.  Scaling regression inputs by dividing by two standard deviations , 2008, Statistics in medicine.

[56]  Rainer Winkelmann,et al.  Subjective well-being and the family: Results from an ordered probit model with multiple random effects , 2004, SSRN Electronic Journal.

[57]  Moses Shayo.  A Model of Social Identity with an Application to Political Economy: Nation, Class, and Redistribution , 2009, American Political Science Review.

[58]  M. Escobar,et al.  Bayesian Density Estimation and Inference Using Mixtures , 1995 .

[59]  D. Soskice,et al.  An Asset Theory of Social Policy Preferences , 2001, American Political Science Review.

[60]  T. Ferguson.  Prior Distributions on Spaces of Probability Measures , 1974 .

[61]  J G Ibrahim,et al.  A semiparametric Bayesian approach to the random effects model. , 1998, Biometrics.

[62]  George Casella,et al.  Estimation in Dirichlet random effects models , 2010, 1002.4756.

[63]  Stephen Nickell,et al.  Biases in Dynamic Models with Fixed Effects , 1981 .

[64]  D. Stasavage,et al.  Religion and Preferences for Social Insurance , 2006 .

[65]  Peter E. Rossi,et al.  Bayesian Statistics and Marketing: Rossi/Bayesian Statistics and Marketing , 2006 .

[66]  I. Neustadt.  Do Religious Beliefs Explain Preferences for Income Redistribution? Experimental Evidence , 2011 .

[67]  Zvi Eckstein,et al.  Why Youths Drop out of High School: The Impact of Preferences , 1999 .

[68]  Lancelot F. James,et al.  Gibbs Sampling Methods for Stick-Breaking Priors , 2001 .

[69]  T. Ferguson.  A Bayesian Analysis of Some Nonparametric Problems , 1973 .

[70]  Gregory J. Wawro,et al.  Estimating Dynamic Panel Data Models in Political Science , 2002, Political Analysis.

[71]  G. Casella,et al.  Nonparametric Priors for Ordinal Bayesian Social Science Models: Specification and Estimation , 2009 .

[72]  Ali Reza Fotouhi,et al.  The initial conditions problem in longitudinal binary process: A simulation study , 2005, Simul. Model. Pract. Theory.

[73]  Marno Verbeek,et al.  Whose wages do unions raise? A dynamic model of unionism and wage rate determination for young men , 1998 .

[74]  J Wakefield,et al.  Cumulative logit models for ordinal data: a case study involving allergic rhinitis severity scores , 2001, Statistics in medicine.

[75]  F. Palm,et al.  Simple Solutions to the Initial Conditions Problem in Multiple Equation Dynamic Panel Data Models with Individual Effects , 2010 .

[76]  Hikaru Hasegawa,et al.  Bayesian Dynamic Panel-Ordered Probit Model and Its Application to Subjective Well-Being , 2009, Commun. Stat. Simul. Comput..

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

[78]  J. Vermunt,et al.  Latent class models in longitudinal research , 2007 .

[79]  The dynamics of perception: modelling subjective wellbeing in a short panel , 2007 .

[80]  M. Aitkin.  A General Maximum Likelihood Analysis of Variance Components in Generalized Linear Models , 1999, Biometrics.

[81]  Raquel Carrasco,et al.  Binary choice panel data models with predetermined variables , 2003 .

[82]  María José García-Zattera,et al.  A Dirichlet process mixture model for the analysis of correlated binary responses , 2007, Comput. Stat. Data Anal..

[83]  Jeremy MG Taylor,et al.  Robust Statistical Modeling Using the t Distribution , 1989 .