• Journal of the Korean Data and Information Science Society
• /
• v.25 no.3
• /
• pp.493-499
• /
• 2014

The Pythagorean won-loss formula postulated by James (1980) indicates the percentage of games as a function of runs scored and runs allowed. Several hundred articles have explored variations which improve RMSE by original formula and their fit to empirical data. This paper considers a variation on the formula which allows for variation of the Pythagorean exponent. We provide the most suitable optimal exponent in the Pythagorean method. We compare it with other methods, such as the Pythagenport by Davenport and Woolner, and the Pythagenpat by Smyth and Patriot. Finally, our results suggest that proposed method is superior to other tractable alternatives under criterion of RMSE.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.2
• /
• pp.349-356
• /
• 2009

In this study, we suggest the estimation method of the relative risk for the unemployment statistics of a small area such as si, gun, gu in Korea. The considered method are the usual pooled estimator, weighted estimator with the inverse of log-variance as weights, and the Jackknife estimator. And we compare with the efficiency of the three estimators by estimating the bias and mean square errors using real data from the 2002 Economically Active Population Survey of Gyeonggi-do. We compute the unemployed rate of male and female in small areas, and then estimate the common relative risk for the unemployed rate between male and female. Also, the stability and reliability of the three estimators for the common relative risk was evaluated using the RB(relative bias) and the RRMSE(relative root mean square error) of these estimators. Finally, the Jackknife estimator turned out to be much more efficient than the other estimators.

• The Korean Journal of Applied Statistics
• /
• v.16 no.1
• /
• pp.1-14
• /
• 2003

In this study, we suggest the method of small area estimation based on the Economically Active Population Survey (EAPS) data in producing unemployment statistics for the local self-government areas (LSGAs) within large areas. The small area estimators considered are design-based indirect estimators such as the synthetic and composite estimators. The jackknife mean square error was used as a measure of accuracy of such small area estimators. The total unemployed and jackknife mean square errors of the 10 LSGAs within the large area of ChoongBuk region are derived from the estimation procedure suggested in this study, using EAPS data of December 2000. The reliability of small area estimators was assessed using the relative bias values and relative root mean square errors of these estimators. We find that under the current Korean EAPS system, the composite estimator turns out to be much more stable than other estimators.

• The Korean Journal of Applied Statistics
• /
• v.19 no.2
• /
• pp.217-230
• /
• 2006

e discuss proper confidence intervals for interval estimation of a low binomial proportion. A large sample surveys are practically executed to find rates of rare diseases, specified industrial disaster, and parasitic infection. Under the conditions of 0 < p ${\leq}$ 0.1 and large n, we compared 6 confidence intervals with mean coverage probability, root mean square error and mean expected widths to search a good one for interval estimation of population proportion p. As a result of comparisons, Mid-p confidence interval is best and AC, score and Jeffreys confidence intervals are next.

• The Korean Journal of Applied Statistics
• /
• v.26 no.6
• /
• pp.943-952
• /
• 2013

Wald, Agresti-Coull, Jeffreys, and Bayes-Laplace methods are commonly used for confidence interval of binomial proportion are applied for prediction intervals. We used coverage probability, mean coverage probability, root mean squared error, and mean expected width for numerical comparisons. From the comparisons, we found that Wald is not proper as for confidence interval and Agresti-Coull is too conservative to differ from confidence interval. However, Jeffrey and Bayes-Laplace are good for prediction interval and Jeffrey is especially desirable as for confidence interval.

• The Korean Journal of Applied Statistics
• /
• v.34 no.4
• /
• pp.579-588
• /
• 2021

Wald, Agresti-Coull, Jeffreys, and Bayes-Laplace methods are commonly used for confidence interval of binomial proportion are applied for prediction intervals. We used coverage probability, mean coverage probability, root mean squared error, and mean expected width for numerical comparisons. From the comparisons, we found that Wald is not proper as for confidence interval and Agresti-Coull is too conservative to differ from confidence interval. However, Jeffrey and Bayes-Laplace are good for prediction interval and Jeffrey is especially desirable as for confidence interval.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.6
• /
• pp.1585-1592
• /
• 2016

Estimation of winning percentage in baseball has always been particularly interesting to many baseball fans. We have fitted models including linear regression and Pythagorean formula to the Korean baseball data of seasons from 1982 to 2015. Using RMSE criterion for both the linear formula and the Pythagorean formula, we compared two models in predicting the actual winning percentage. Pythagorean expectation is superior to linear formula when there is either high or low winning percentage. Two methods yield very similar efficiencies when the actual winning percentage is about 50%. To understand and use for estimating winning percentage, it is easier linear formula as estimated equations.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2006.05a
• /
• pp.1822-1829
• /
• 2006

본 연구에서는 계산된 유량과 실측 유량을 비교하여 Clark 단위도 방법의 매개변수를 추정하고자 하였다. 오산천과 진위천 상류유역에 대하여 Arcview와 WMS로 지형자료에 대한 전 처리를 한후, HEC-HMS 프로그램을 이용하여 유출량을 산정하였다. 2001년부터 2005년까지 4개의 사상에 대하여 강우량, 기흥저수지와 이동저수지의 실제 방류량을 이용하여 유출량을 산정하였으며, Clark 모형의 매개변수를 Russel 공식, Sabol 공식 및 HEC-HMS 프로그램에 내장된 Nelder-Mead 최적화 방법을 이용하여 매개변수를 각각 산정하여 회화 지점의 실측 유출량과 비교.평가하였다. 빈도가 큰 유출사상의 경우에는 Sabol 식을 적용한 결과가 Russel 식을 적용한 모의결과보다 첨두유량의 재현성이 우수하게 나타났으며, 유출량이 작은 경우에는 Russel 식을 적용한 모의결과가 우수하였다. 첨두가 중제곱평균제곱근오차, 잔차자승의 합, 절대잔차의 합 등 3가지의 서로다른 목적함수를 적용하여 매개변수를 자동 보정하였을 때, 목적함수에 따른 첨두유량의 오차는 거의 동일하였으며, 첨두시간에 대한 오차는 첨두가중제곱평균제곱근오차를 적용했을 때 가장 작은 것으로 분석되었다. 그리고 Clark 유역 추적모형의 자동보정을 통하여 추정한 매개변수인 도달시간과 저류상수는 강우사상에 따라서 변동하는 특성을 나타내기 때문에 최적의 도달시간 및 저류상수는 홍수사상별로 추정되어야 하며 이 결과는 홍수량 산정을 위한 매개변수 추정과정의 비유일성 및 복잡성을 암시하고 있다.

• Journal of the Korea Convergence Society
• /
• v.7 no.5
• /
• pp.175-180
• /
• 2016

The demand for accurate freeform apsheric surface is increasing to satisfy the optical performance. In this paper, we develop the algorithm for opto-mechatronics convergence, that reconstruct the surface 3D profiles from the curvarure data along two orthogonal directions. A synthetic freeform surface with 8.4 m diameter was simulated for the testing. The simulation results show that the reconstruction error is 0.065 nm PV(Peak-to-valley) and 0.013 nm RMS(Root mean square) residual difference. Finally the sensitivity to noise is diagnosed for probe position error, the simulation results proving that the suggested method is robust to position error.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.3
• /
• pp.653-661
• /
• 2016

In this paper, we provide a suitable optimal exponent in the generalized Pythagorean theorem and propose to use the logistic model & the probit model to estimate the winning rate in Korean professional baseball league. Under a criterion of root-mean-square-error (RMSE), the efficiencies of the proposed models have been compared with those of the Pythagorean theorem. We use the team historic win-loss records of Korean professional baseball league from 1982 to the first half of 2015, and the proposed methods show slight outperformances over the generalized Pythagorean method under the criterion of RMSE.