초록 close

야구에서 승률을 예측하는 방법 중 하나는 Bill James의 피타고라스 정리로써 승률(W)은 팀 득점(RS)의 제곱과 실점(RA)의 제곱을 이용하여 예측된다. 본 연구에서는 한국 프로야구 데이터와 최적판단기준으로 평균제곱오차의 제곱근(RMSE)을 이용하여 피타고라스 정리의 최적지수 값을 찾아보았다. 또한 홈팀의 편의 효과를 연구하였으며 피타고라스 정리의 선형근사식을 제안하였다.


The primary method for determining winning percentage in baseball is Bill James' Pythagorean method. The Pythagorean theorem, as James called it, was a formula designed to relate how many runs a team scored and allowed to its won-lost record.In this study, we test an application of Pythagorean theorem to the Korean Pro-Baseball. We provide the most suitable optimal exponent in the Pythagorean Theorem under criterion of root-mean-square error(RMSE). We give some equation for the best choice of the exponent approximately and investigate the effect of bias against the home team. Also we suggest some approximate linear formula for Pythagorean theorem.In Conclusion, Bill James' Pythagorean method is a fairly good method for Korean Pro - Baseball. Moreover, special relationship between the number of wins and losses for a baseball team and the number of runs scored and number of runs allowed in Korea is very similar to the that of the Major League teams in America.