• 한국환경과학회지
• /
• 제22권8호
• /
• pp.965-977
• /
• 2013

Reliable long-term streamflow forecasting is invaluable for water resource planning and management which allocates water supply according to the demand of water users. It is necessary to get probabilistic forecasts to establish risk-based reservoir operation policies. Probabilistic forecasts may be useful for the users who assess and manage risks according to decision-making responding forecasting results. Probabilistic forecasting of seasonal inflow to Andong dam is performed and assessed using selected predictors from sea surface temperature and 500 hPa geopotential height data. Categorical probability forecast by Piechota's method and logistic regression analysis, and probability forecast by conditional probability density function are used to forecast seasonal inflow. Kernel density function is used in categorical probability forecast by Piechota's method and probability forecast by conditional probability density function. The results of categorical probability forecasts are assessed by Brier skill score. The assessment reveals that the categorical probability forecasts are better than the reference forecasts. The results of forecasts using conditional probability density function are assessed by qualitative approach and transformed categorical probability forecasts. The assessment of the forecasts which are transformed to categorical probability forecasts shows that the results of the forecasts by conditional probability density function are much better than those of the forecasts by Piechota's method and logistic regression analysis except for winter season data.

• 보건행정학회지
• /
• 제11권1호
• /
• pp.1-18
• /
• 2001

The purpose of the present study was to assess the agreement of survival probability estimated by International Classification of Diseases l0th Edition(ICD-10) based International Classification of Diseases based Injury Severity Score(ICISS) with professional panel's judgment on preventable death. ICISS has a promise as an alternative to Trauma and Injury Severity Score(TRISS) which have served as a standard measure of trauma severity, but requires more validation studies. Furthermore as original version of ICISS was based ICD-9CM, it is necessary to test its performance employing ICD-10 which has been used in Korea and is expected to replace ICD-9 in many countries sooner or later. Methods : For 1997 and 1998 131 trauma deaths and 1,785 blunt trauma inpatients from 6 emergency medical centers were randomly sampled and reviewed. Trauma deaths were reviewed by professional panels with hospital records and survival probability of trauma inpatients was assessed using ICD-10 based ICISS. For trauma mortality degree of agreement between ICISS survival probability with judgment of professional panel on preventable death was assessed and correlation between W-score and preventable death rate by each emergency medical center was assessed. Results : Overall agreement rate of ICISS survival probability with preventable death judged by professional panel was 66.4%(kappa statistic 0.36). Spearman's correlation coefficient between W-score and preventable death rate by each emergency medical center was -0.77(p=0.07) and Pearson's correlation coefficient between them was -0.90(p=0.01). Conclusions : The agreement rate of ICD-10 based ICISS survival probability with of professional panel's judgment on preventable death was similar to TRISS. The W-scores of emergency medical centers derived from ICD-10 based ICISS were highly correlated with preventable death rates of them with marginal statistical significance.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권20호
• /
• pp.8647-8650
• /
• 2014

Background: Ovarian cancer is the most common cancer cause of gynecologic cancer deaths. In order to increase the likelihood of patient survival through primary operation by gyneco-oncologists, an appropriate algorithm for referral is considered here. Materials and Methods: Suspicious adnexal mass cases including ovarian malignancy probability score-1 (OMPS1) scores between 2.3-3.65 are re-evaluated by OMPS2. Sensitivity and specificity of each score were determined. Results: Sensitivity and specificity with a 3.82 score of OMPS2 in the studied subgroup (OMPS1 scores between 2.3-3.65) were 64% and 76.9% respectively. Conclusions: Management of OMPS1 scores of below 2.3 with sensitivity of 100% and above 3.65 with specificity of 72.9% is clear. In the subgroup of cases with OMPS1 score between 2.3-3.65, OMPS2 is helpful for triage with a cutoff score of 3.82.

• 산업공학
• /
• 제24권4호
• /
• pp.323-329
• /
• 2011

We develop a stochastic model to predict the score of a soccer match. We describe the scoring process of the soccer match as a markovian arrival process (MAP). To do this, we define a two-state underlying Markov chain, in which the two states represent the offense and defense states of the two teams to play. Then, we derive the probability vector generating function of the final scores. Numerically inverting this generating function, we obtain the desired probability distribution of the scores. Sample numerical examples are given at the end to demonstrate how to utilize this result to predict the final score of the match.

• Communications for Statistical Applications and Methods
• /
• 제29권2호
• /
• pp.263-275
• /
• 2022

Use of appropriate technique for non-response occurring in sample survey improves the accuracy of the estimation. Many studies have been conducted for handling non-ignorable non-response and commonly the response probability is estimated using the propensity score method. Recently, post-stratification method to obtain the response probability proposed by Chung and Shin (2017) reduces the effect of bias and gives a good performance in terms of the MSE. In this study, we propose a new response probability estimation method by combining the propensity score adjustment method using the logistic regression model with post-stratification method used in Chung and Shin (2017). The superiority of the proposed method is confirmed through simulation.

• 응용통계연구
• /
• 제22권1호
• /
• pp.29-39
• /
• 2009

신용평가 연구에서 부도율분포를 기반으로 부도기업과 정상기업의 판별력을 탐색하는 방법 중의 하나로 ROC와 CAP 곡선을 사용한다. 부도와 정상기업을 분류하는 절단점의 변동에 따라 구한 여러 부도비율을 통해 ROC와 CAP 곡선을 작성하는데 곡선의 각 좌표에 대응하는 절단점을 탐색하기 어렵다. 본 연구에서는 ROC와 CAP 곡선을 나타내는 부도비율들의 함수를 이용하여 조정된 ROC와 CAP곡선을 제안한다. 조정된 ROC와 CAP 곡선을 통해 절단점과의 관계를 파악할 수 있으며, 최적의 절단점을 식별할 수 있다. 또한 부도와 정상기업에 관한 분포함수의 동일성을 검정하는 Kolmogorov - Smirnov 통계량과 조정된 ROC와 CAP 곡선을 통해 얻은 최적 절단점의 관계를 토론한다.

• Communications for Statistical Applications and Methods
• /
• 제27권6호
• /
• pp.675-688
• /
• 2020

In survival analysis of observational data, the inverse probability weighting method and the Cox proportional hazards model are widely used when estimating the causal effects of multiple-valued treatment. In this paper, the two kinds of weights have been examined in the inverse probability weighting method. We explain the reason why the stabilized weight is more appropriate when an inverse probability weighting method using the generalized propensity score is applied. We also emphasize that a marginal hazard ratio and the conditional hazard ratio should be distinguished when defining the hazard ratio as a treatment effect under the Cox proportional hazards model. A simulation study based on real data is conducted to provide concrete numerical evidence.

• Korean Journal of Radiology
• /
• 제25권4호
• /
• pp.328-330
• /
• 2024

• Journal of the Korean Statistical Society
• /
• 제32권4호
• /
• pp.373-384
• /
• 2003

In this paper, we formulate multivariate one-sided alternatives and propose a class of nonparametric tests for possibly right censored data. We obtain the asymptotic tail probability (or p-value) by showing that our proposed test statistics have asymptotically multivariate normal distributions. Also, we illustrate our procedure with an example and compare it with other procedures in terms of empirical powers for the bivariate case. Finally, we discuss some properties of our test.

• Communications for Statistical Applications and Methods
• /
• 제17권3호
• /
• pp.309-318
• /
• 2010

The construction of asymptotic confidence intervals is considered for the difference of binomial proportions in two doubly sampled data subject to false-positive error. The coverage behaviors of several likelihood based confidence intervals and a Bayesian confidence interval are examined. It is shown that a hierarchical Bayesian approach gives a confidence interval with good frequentist properties. Confidence interval based on the Rao score is also shown to have good performance in terms of coverage probability. However, the Wald confidence interval covers true value less often than nominal level.