Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Nonparametric estimation of the distribution function in contingent valuation models
AU - Leslie, David S.
AU - Kohn, Robert
AU - Fiebig, Denzil G.
PY - 2009/9/1
Y1 - 2009/9/1
N2 - Contingent valuation models are used in Economics to value non-market goods and can be expressed as binary choice regression models with oneof the regression coe±cients ¯xed. A method for °exibly estimating the link func-tion of such binary choice model is proposed by using a Dirichlet process mixtureprior on the space of all latent variable distributions, instead of the more restricteddistributions in earlier papers. The model is estimated using a novel MCMC sam-pling scheme that avoids the high autocorrelations in the iterates that usually arisewhen sampling latent variables that are mixtures. The method allows for variableselection and is illustrated using simulated and real data.
AB - Contingent valuation models are used in Economics to value non-market goods and can be expressed as binary choice regression models with oneof the regression coe±cients ¯xed. A method for °exibly estimating the link func-tion of such binary choice model is proposed by using a Dirichlet process mixtureprior on the space of all latent variable distributions, instead of the more restricteddistributions in earlier papers. The model is estimated using a novel MCMC sam-pling scheme that avoids the high autocorrelations in the iterates that usually arisewhen sampling latent variables that are mixtures. The method allows for variableselection and is illustrated using simulated and real data.
KW - binary choice regression
KW - Dirichlet process
KW - latent variable
KW - mixture model
KW - variable selection
U2 - 10.1214/09-BA421
DO - 10.1214/09-BA421
M3 - Journal article
VL - 4
SP - 573
EP - 598
JO - Bayesian Analysis
JF - Bayesian Analysis
SN - 1936-0975
IS - 3
ER -