Log-Linear Bayesian Additive Regression Trees for Multinomial Logistic and Count Regression Models
نویسندگان
چکیده
We introduce Bayesian additive regression trees (BART) for log-linear models including multinomial logistic and count with zero-inflation overdispersion. BART has been applied to nonparametric mean binary classification problems in a range of settings. However, existing applications have mostly limited Gaussian “data,” either observed or latent. This is primarily because efficient MCMC algorithms are available likelihoods. But while many useful naturally cast terms latent variables, others not—including considered this article. develop new data augmentation strategies carefully specified prior distributions these models. Like the original prior, constructed calibrated be flexible guarding against overfitting. Together priors schemes allow us implement an sampler outside context The utility methods illustrated examples application previously published dataset. Supplementary materials article online.
منابع مشابه
Bayesian Multinomial Logistic Regression for Author Identification
Motivated by high-dimensional applications in authorship atttribution, we describe a Bayesian multinomial logistic regression model together with an associated learning algorithm.
متن کاملBayesian Additive Regression Trees
We develop a Bayesian “sum-of-trees” model where each tree is constrained by a regularization prior to be a weak learner, and fitting and inference are accomplished via an iterative Bayesian backfitting MCMC algorithm that generates samples from a posterior. Effectively, BART is a nonparametric Bayesian regression approach which uses dimensionally adaptive random basis elements. Motivated by en...
متن کاملParallel Bayesian Additive Regression Trees
Bayesian Additive Regression Trees (BART) is a Bayesian approach to flexible non-linear regression which has been shown to be competitive with the best modern predictive methods such as those based on bagging and boosting. BART offers some advantages. For example, the stochastic search Markov Chain Monte Carlo (MCMC) algorithm can provide a more complete search of the model space and variation ...
متن کاملBART: Bayesian Additive Regression Trees
We develop a Bayesian “sum-of-trees” model where each tree is constrained by a regularization prior to be a weak learner, and fitting and inference are accomplished via an iterative Bayesian backfitting MCMC algorithm that generates samples from a posterior. Effectively, BART is a nonparametric Bayesian regression approach which uses dimensionally adaptive random basis elements. Motivated by en...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of the American Statistical Association
سال: 2021
ISSN: ['0162-1459', '1537-274X', '2326-6228', '1522-5445']
DOI: https://doi.org/10.1080/01621459.2020.1813587