On Marginal Likelihood Computation in Change-Point Models

Change-point models are useful for modeling time series subject to structural breaks. For interpretation and forecasting, it is essential to estimate correctly the number of change points in this class of models. In Bayesian inference, the number of change points is typically chosen by the marginal likelihood criterion, computed by Chib's method. This method requires one to select a value in the parameter space at which the computation is performed. Bayesian inference for a change-point dynamic regression model and the computation of its marginal likelihood are explained. Motivated by results from three empirical illustrations, a simulation study shows that Chib's method is robust with respect to the choice of the parameter value used in the computations, among posterior mean, mode and quartiles. However, taking into account the precision of the marginal likelihood estimator, the overall recommendation is to use the posterior mode or median. Furthermore, the performance of the Bayesian information criterion, which is based on maximum likelihood estimates, in selecting the correct model is comparable to that of the marginal likelihood.

[1]  Chang-Jin Kim,et al.  Common Stochastic Trends, Common Cycles, and Asymmetry in Economic Fluctuations , 2000 .

[2]  Luc Bauwens,et al.  Bayesian Inference in Dynamic Econometric Models , 2000 .

[3]  J. Dávila,et al.  On the fiscal treatment of life expectancy related choices , 2009 .

[4]  S. Chib.  Estimation and comparison of multiple change-point models , 1998 .

[5]  Nicolas Boccard,et al.  Entry accommodation under multiple commitment strategies: judo economics revisited , 2009 .

[6]  J. Rombouts,et al.  Nonparametric Copula-Based Test for Conditional Independence with Applications to Granger Causality , 2012 .

[7]  M. Newton.  Approximate Bayesian-inference With the Weighted Likelihood Bootstrap , 1994 .

[8]  Claire Dujardin,et al.  Neighbourhood effects and endogeneity issues , 2009 .

[9]  To Bridge, to Warp or to Wrap? A Comperative Study of Monte Carlo Methods for Efficient Evaluation of Marginal Likelihood , 2009 .

[10]  Sylvia Frühwirth-Schnatter,et al.  Computational Statistics and Data Analysis Marginal Likelihoods for Non-gaussian Models Using Auxiliary Mixture Sampling , 2022 .

[11]  C. d'Aspremont,et al.  Household behavior and individual autonomy , 2009 .

[12]  Y. Smeers,et al.  Multi-assets real options , 2009 .

[13]  Olivier Bos,et al.  All-Pay Auctions with Endogenous Rewards , 2009 .

[14]  James D. Hamilton.  A New Approach to the Economic Analysis of Nonstationary Time Series and the Business Cycle , 1989 .

[15]  Yasuhiro Omori,et al.  Leverage, heavy-tails and correlated jumps in stochastic volatility models , 2007, Comput. Stat. Data Anal..

[16]  James Renegar,et al.  A mathematical view of interior-point methods in convex optimization , 2001, MPS-SIAM series on optimization.

[17]  D. Peeters,et al.  Residential equilibrium in a multifractal metropolitan area , 2010 .

[18]  N. Shephard,et al.  Likelihood INference for Discretely Observed Non-linear Diffusions , 2001 .

[19]  Chang‐Jin Kim,et al.  Has the U.S. Economy Become More Stable? A Bayesian Approach Based on a Markov-Switching Model of the Business Cycle , 1999, Review of Economics and Statistics.

[20]  S. Frühwirth-Schnatter.  Estimating Marginal Likelihoods for Mixture and Markov Switching Models Using Bridge Sampling Techniques , 2004 .

[21]  John M. Olin.  Calculating posterior distributions and modal estimates in Markov mixture models , 1996 .

[22]  Roberta Paroli,et al.  Bayesian inference in non-homogeneous Markov mixtures of periodic autoregressions with state-dependent exogenous variables , 2008, Comput. Stat. Data Anal..

[23]  L. Wasserman,et al.  Computing Bayes Factors by Combining Simulation and Asymptotic Approximations , 1997 .

[24]  S. Chib.  Marginal Likelihood from the Gibbs Output , 1995 .

[25]  Laurence A. Wolsey,et al.  Constrained Infinite Group Relaxations of MIPs , 2010, SIAM J. Optim..

[26]  Bradley P. Carlin,et al.  Bayesian measures of model complexity and fit , 2002 .

[27]  A. Gelfand,et al.  Bayesian Model Choice: Asymptotics and Exact Calculations , 1994 .

[28]  Chang-Jin Kim,et al.  The Structural Break in the Equity Premium , 2005 .

[29]  Davide Pettenuzzo,et al.  Forecasting Time Series Subject to Multiple Structural Breaks , 2004, SSRN Electronic Journal.

[30]  S. Zanaj,et al.  On uncertainty when it affects successive markets , 2010 .

[31]  Stephen Gordon,et al.  Learning, Forecasting and Structural Breaks , 2008 .

[32]  Nicolas Boccard,et al.  Regulating Quality by Regulating Quantity: A Case against Minimum Quality Standards , 2008 .

[33]  C. Liu,et al.  Are There Structural Breaks in Realized Volatility , 2008 .

[34]  C. Robert,et al.  Deviance information criteria for missing data models , 2006 .

[35]  Georg Dorffner,et al.  A comparison of Bayesian model selection based on MCMC with an application to GARCH-type models , 2006 .

[36]  J. Stock,et al.  Evidence on Structural Instability in Macroeconomic Time Series Relations , 1994 .

[37]  Lorne D. Johnson,et al.  Maximizing equity market sector predictability in a Bayesian time-varying parameter model , 2008, Comput. Stat. Data Anal..

[38]  François Maniquet,et al.  On the informational efficiency of simple scoring rules , 2011, J. Econ. Theory.

[39]  M. Iorio.  Discussion to the paper by Spiegelhalter et al., “Bayesian measures of complexity and fit” , 2002 .

[40]  Xiao-Li Meng,et al.  SIMULATING RATIOS OF NORMALIZING CONSTANTS VIA A SIMPLE IDENTITY: A THEORETICAL EXPLORATION , 1996 .