157274-Thumbnail Image.png
Description
Bayesian Additive Regression Trees (BART) is a non-parametric Bayesian model

that often outperforms other popular predictive models in terms of out-of-sample error. This thesis studies a modified version of BART called Accelerated Bayesian Additive Regression Trees (XBART). The study consists of

Bayesian Additive Regression Trees (BART) is a non-parametric Bayesian model

that often outperforms other popular predictive models in terms of out-of-sample error. This thesis studies a modified version of BART called Accelerated Bayesian Additive Regression Trees (XBART). The study consists of simulation and real data experiments comparing XBART to other leading algorithms, including BART. The results show that XBART maintains BART’s predictive power while reducing its computation time. The thesis also describes the development of a Python package implementing XBART.


Download restricted.

Details

Title
  • A study of accelerated Bayesian additive regression trees
Contributors
Date Created
2019
Resource Type
  • Text
  • Collections this item is in
    Note
    • thesis
      Partial requirement for: M.S., Arizona State University, 2019
    • bibliography
      Includes bibliographical references (pages 37-38)
    • Field of study: Statistics

    Citation and reuse

    Statement of Responsibility

    by Saar Yalov

    Machine-readable links