search for


A Poisson directed acyclic graphical model for analyzing Korean baseball batter’s characteristics
Journal of the Korean Data & Information Science Society 2019;30:873-84
Published online July 31, 2019;
© 2019 Korean Data and Information Science Society.

Hyewon Park1 · Gunwoong Park2

12Department of Statistics, University of Seoul
Correspondence to: Assistant professor, Department of Statistics, University of Seoul, Seoul 02504, Korea. E-mail:

† This work was supported by the ICT R&D program of MSIT/IITP. [2018-0-01569, An R&D Project of Customized Shopping & Tour Promotion Service for Foreign Travelers Based on CRM]
Received May 4, 2019; Revised June 4, 2019; Accepted June 14, 2019.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License ( which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
In baseball, the sabermetrics has been more important which measures the performance of baseball players in a refined way. However, many works focus on a new measure of player’s overall performance without considering the relationships between baseball statistics. Hence, the main objective of this study is to find a direct or causal network of batter’s statistics using a Bayesian network or a directed acyclic graphical (DAG) model that models the probabilistic dependencies of statistics. Since the baseball statistics we consider are multivariate count data, we applied the Poisson directed acyclic graphical model and we also applied the ODS algorithm to learn the players’ batting statistics networks. We expect to find a new perspective of hitter ability index or sabermetrics using the relationship between indicators.
Keywords : Bayesian network, directed acyclic graphical models, multivariate count data, sabermetrics.