Semiparametric Bayesian inference in smooth coefficient models

G.M. Koop, J. Tobias

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

We describe procedures for Bayesian estimation and testing in cross-sectional, panel data and nonlinear smooth coefficient models. The smooth coefficient model is a generalization of the partially linear or additive model wherein coefficients on linear explanatory variables are treated as unknown functions of an observable covariate. In the approach we describe, points on the regression lines are regarded as unknown parameters and priors are placed on differences between adjacent points to introduce the potential for smoothing the curves. The algorithms we describe are quite simple to implement - for example, estimation, testing and smoothing parameter selection can be carried out analytically in the cross-sectional smooth coefficient model. We apply our methods using data from the National Longitudinal Survey of Youth (NLSY). Using the NLSY data we first explore the relationship between ability and log wages and flexibly model how returns to schooling vary with measured cognitive ability. We also examine a model of female labor supply and use this example to illustrate how the described techniques can been applied in nonlinear settings.
LanguageEnglish
Pages283-315
Number of pages32
JournalJournal of Econometrics
Volume134
DOIs
Publication statusPublished - 2006

Fingerprint

Bayesian inference
Coefficient
Labor Supply
Regression line
Partially Linear Model
Testing
Model
Additive Models
Parameter Selection
Smoothing Parameter
Wages
Bayesian Estimation
Panel Data
Unknown Parameters
Covariates
Smoothing
Adjacent
Coefficients
Bayesian Inference
Vary

Keywords

  • bayesian econometrics
  • semiparametric regression
  • econometrics
  • economics

Cite this

@article{f409428d3b934d098b407ae6ea7f515d,
title = "Semiparametric Bayesian inference in smooth coefficient models",
abstract = "We describe procedures for Bayesian estimation and testing in cross-sectional, panel data and nonlinear smooth coefficient models. The smooth coefficient model is a generalization of the partially linear or additive model wherein coefficients on linear explanatory variables are treated as unknown functions of an observable covariate. In the approach we describe, points on the regression lines are regarded as unknown parameters and priors are placed on differences between adjacent points to introduce the potential for smoothing the curves. The algorithms we describe are quite simple to implement - for example, estimation, testing and smoothing parameter selection can be carried out analytically in the cross-sectional smooth coefficient model. We apply our methods using data from the National Longitudinal Survey of Youth (NLSY). Using the NLSY data we first explore the relationship between ability and log wages and flexibly model how returns to schooling vary with measured cognitive ability. We also examine a model of female labor supply and use this example to illustrate how the described techniques can been applied in nonlinear settings.",
keywords = "bayesian econometrics, semiparametric regression, econometrics, economics",
author = "G.M. Koop and J. Tobias",
year = "2006",
doi = "10.1016/j.jeconom.2005.06.027",
language = "English",
volume = "134",
pages = "283--315",
journal = "Journal of Econometrics",
issn = "0304-4076",

}

Semiparametric Bayesian inference in smooth coefficient models. / Koop, G.M.; Tobias, J.

In: Journal of Econometrics, Vol. 134, 2006, p. 283-315.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Semiparametric Bayesian inference in smooth coefficient models

AU - Koop, G.M.

AU - Tobias, J.

PY - 2006

Y1 - 2006

N2 - We describe procedures for Bayesian estimation and testing in cross-sectional, panel data and nonlinear smooth coefficient models. The smooth coefficient model is a generalization of the partially linear or additive model wherein coefficients on linear explanatory variables are treated as unknown functions of an observable covariate. In the approach we describe, points on the regression lines are regarded as unknown parameters and priors are placed on differences between adjacent points to introduce the potential for smoothing the curves. The algorithms we describe are quite simple to implement - for example, estimation, testing and smoothing parameter selection can be carried out analytically in the cross-sectional smooth coefficient model. We apply our methods using data from the National Longitudinal Survey of Youth (NLSY). Using the NLSY data we first explore the relationship between ability and log wages and flexibly model how returns to schooling vary with measured cognitive ability. We also examine a model of female labor supply and use this example to illustrate how the described techniques can been applied in nonlinear settings.

AB - We describe procedures for Bayesian estimation and testing in cross-sectional, panel data and nonlinear smooth coefficient models. The smooth coefficient model is a generalization of the partially linear or additive model wherein coefficients on linear explanatory variables are treated as unknown functions of an observable covariate. In the approach we describe, points on the regression lines are regarded as unknown parameters and priors are placed on differences between adjacent points to introduce the potential for smoothing the curves. The algorithms we describe are quite simple to implement - for example, estimation, testing and smoothing parameter selection can be carried out analytically in the cross-sectional smooth coefficient model. We apply our methods using data from the National Longitudinal Survey of Youth (NLSY). Using the NLSY data we first explore the relationship between ability and log wages and flexibly model how returns to schooling vary with measured cognitive ability. We also examine a model of female labor supply and use this example to illustrate how the described techniques can been applied in nonlinear settings.

KW - bayesian econometrics

KW - semiparametric regression

KW - econometrics

KW - economics

U2 - 10.1016/j.jeconom.2005.06.027

DO - 10.1016/j.jeconom.2005.06.027

M3 - Article

VL - 134

SP - 283

EP - 315

JO - Journal of Econometrics

T2 - Journal of Econometrics

JF - Journal of Econometrics

SN - 0304-4076

ER -