Bayesian robust inference of sample selection using selection-t models
From MaRDI portal
Abstract: Heckman selection model is the most popular econometric model in analysis of data with sample selection. However, selection models with Normal errors cannot accommodate heavy tails in the error distribution. Recently, Marchenko and Genton proposed a selection-t model to perform frequentist' robust analysis of sample selection. Instead of using their maximum likelihood estimates, our paper develops new Bayesian procedures for the selection-t models with either continuous or binary outcomes. By exploiting the Normal mixture representation of the t distribution, we can use data augmentation to impute the missing data, and use parameter expansion to sample the restricted covariance matrices. The Bayesian procedures only involve simple steps, without calculating analytical or numerical derivatives of the complicated log likelihood functions. Simulation studies show the vulnerability of the selection models with Normal errors, as well as the robustness of the selection models with t errors. Interestingly, we find evidence of heavy-tailedness in three real examples analyzed by previous studies, and the conclusions about the existence of selection effect are very sensitive to the distributional assumptions of the error terms.
Recommendations
Cites work
- scientific article; zbMATH DE number 1556163 (Why is no real title available?)
- scientific article; zbMATH DE number 1834445 (Why is no real title available?)
- scientific article; zbMATH DE number 5274820 (Why is no real title available?)
- A Bayesian analysis of the multinomial probit model using marginal data augmentation
- A Bayesian analysis of the multinomial probit model with fully identified parameters
- A Heckman selection-\(t\) model
- Asymptotic Statistics
- Bayesian Analysis of Binary and Polychotomous Response Data
- Bayesian inference in a sample selection model
- Bayesian inference in a simultaneous equation model with limited dependent variables
- Econometric analysis of cross section and panel data.
- Efficient ML estimation of the multivariate normal distribution from incomplete data
- Generalized Econometric Models with Selectivity
- Learning about the across-regime correlation in switching regression models
- Monte Carlo strategies in scientific computing
- Nonparametric Estimation of Sample Selection Models
- Parameter Expansion for Data Augmentation
- Parameter expansion to accelerate EM: the PX-EM algorithm
- Sample Selection Bias as a Specification Error
- Seeking efficient data augmentation schemes via conditional and marginal augmentation
- Semiparametric estimation of censored selection models with a nonparametric selection mechanism
- The Calculation of Posterior Distributions by Data Augmentation
Cited in
(21)- A Heckman selection-\(t\) model
- Inverse regression approach to robust nonlinear high-to-low dimensional mapping
- Copula based generalized additive models for location, scale and shape with non-random sample selection
- Correcting for sample selection bias in Bayesian distributional regression models
- On the Conditional Distribution of the Multivariate t Distribution
- Performance of asymmetric links and correction methods for imbalanced data in binary regression
- Heckman selection-\(t\) model: parameter estimation via the EM-algorithm
- Comment: Reflections on the Deconfounder
- Birnbaum–Saunders sample selection model
- Bayesian hierarchical robust factor analysis models for partially observed sample-selection data
- Bayesian analysis of semiparametric Bernstein polynomial regression models for data with sample selection
- Robust inference in sample selection models
- Bayesian inference in a sample selection model with multiple selection rules
- Copula selection models for non-Gaussian outcomes that are missing not at random
- A sample selection model with skew-normal distribution
- Bayesian inference in a sample selection model
- Robust modeling using non-elliptically contoured multivariate \(t\) distributions
- Sample selection models for count data in R
- Bivariate symmetric Heckman models and their characterization
- Robust discrete choice models with \(t\)-distributed kernel errors
- New EM-type algorithms for the Heckman selection model
This page was built for publication: Bayesian robust inference of sample selection using selection-\(t\) models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q392110)
