Open Access
2023 Convergence properties of data augmentation algorithms for high-dimensional robit regression
Sourav Mukherjee, Kshitij Khare, Saptarshi Chakraborty
Author Affiliations +
Electron. J. Statist. 17(1): 19-69 (2023). DOI: 10.1214/22-EJS2098

Abstract

The logistic and probit link functions are the most common choices for regression models with a binary response. However, these choices are not robust to the presence of outliers/unexpected observations. The robit link function, which is equal to the inverse CDF of the Student’s t-distribution, provides a robust alternative to the probit and logistic link functions. A multivariate normal prior for the regression coefficients is the standard choice for Bayesian inference in robit regression models. The resulting posterior density is intractable and a Data Augmentation (DA) Markov chain is used to generate approximate samples from the desired posterior distribution. Establishing geometric ergodicity for this DA Markov chain is important as it provides theoretical guarantees for asymptotic validity of MCMC standard errors for desired posterior expectations/quantiles. Previous work [16] established geometric ergodicity of this robit DA Markov chain assuming (i) the sample size n dominates the number of predictors p, and (ii) an additional constraint which requires the sample size to be bounded above by a fixed constant which depends on the design matrix X. In particular, modern high-dimensional settings where n<p are not considered. In this work, we show that the robit DA Markov chain is trace-class (i.e., the eigenvalues of the corresponding Markov operator are summable) for arbitrary choices of the sample size n, the number of predictors p, the design matrix X, and the prior mean and variance parameters. The trace-class property implies geometric ergodicity. Moreover, this property allows us to conclude that the sandwich robit chain (obtained by inserting an inexpensive extra step in between the two steps of the DA chain) is strictly better than the robit DA chain in an appropriate sense, and enables the use of recent methods to estimate the spectral gap of trace class DA Markov chains.

Citation

Download Citation

Sourav Mukherjee. Kshitij Khare. Saptarshi Chakraborty. "Convergence properties of data augmentation algorithms for high-dimensional robit regression." Electron. J. Statist. 17 (1) 19 - 69, 2023. https://doi.org/10.1214/22-EJS2098

Information

Received: 1 December 2021; Published: 2023
First available in Project Euclid: 6 January 2023

MathSciNet: MR4529503
zbMATH: 07649357
arXiv: 2112.10349
Digital Object Identifier: 10.1214/22-EJS2098

Subjects:
Primary: 60J05 , 60J20

Keywords: geometric ergodicity , high-dimensional binary regression , Markov chain Monte Carlo , robust model , trace class

Vol.17 • No. 1 • 2023
Back to Top