• 응용통계연구
• /
• 제4권1호
• /
• pp.33-45
• /
• 1991

변화시점 모형은 지금까지 한 시점에서 단 한 개의 관측자료를 갖는 모형만 생각해 왔다. 이러한 모형을 확장시켜 각 시점에 한 개 이상의 관측자료를 갖는 변화시점 모형을 생각한다. 이러한 모형에서 비모수적인 단측 그리고 양측 검정법을 찾았다. 검정 통계량은 지금까지 소개된 검정 통계량 형태를 확장시킨 형태이고 이들의 귀무가설 분포를 구하여 보았다. 또한 Monte Carlo연구를 통해 이들의 검정력을 비교해 보았다.

• Communications for Statistical Applications and Methods
• /
• 제29권5호
• /
• pp.499-512
• /
• 2022

Intervention measures have been implemented worldwide to reduce the spread of the COVID-19 outbreak. The COVID-19 outbreak has occured in several waves of infection, so this paper is divided into three groups, namely those countries who have passed the pandemic period, those countries who are still experiencing a single-wave pandemic, and those countries who are experiencing a multi-wave pandemic. The purpose of this study is to develop a multi-wave Richards model with several changepoint detection methods so as to obtain more accurate prediction results, especially for the multi-wave case. We investigated epidemiological trends in different countries from January 2020 to October 2021 to determine the temporal changes during the epidemic with respect to the intervention strategy used. In this article, we adjust the daily cumulative epidemiological data for COVID-19 using the logistic growth model and the multi-wave Richards curve development model. The changepoint detection methods used include the interpolation method, the Pruned Exact Linear Time (PELT) method, and the Binary Segmentation (BS) method. The results of the analysis using 9 countries show that the Richards model development can be used to analyze multi-wave data using changepoint detection so that the initial data used for prediction on the last wave can be determined precisely. The changepoint used is the coincident changepoint generated by the PELT and BS methods. The interpolation method is only used to find out how many pandemic waves have occurred in given a country. Several waves have been identified and can better describe the data. Our results can find the peak of the pandemic and when it will end in each country, both for a single-wave pandemic and a multi-wave pandemic.

• 응용통계연구
• /
• 제7권1호
• /
• pp.35-46
• /
• 1994

이변량 변화시점 모형에서 위치모수에 대한 비모수적 방법인 순위-모양 검정법을 제시하였다. 이를 경험적인 검정력을 통하여 모수적인 검정과 비교한 결과, 귀무가설분포가 이변량 정규분포일 때를 제외하고는 순위-모양 검정이 월등히 우수함을 알 수 있었다. 또한 변화시점에 대한 점추정량들을 경험적인 평균제곱오차를 이용하여 비교 분석하였다.

• Journal of the Korean Statistical Society
• /
• 제31권1호
• /
• pp.1-16
• /
• 2002

Since changepoint identification is important in many data analysis problem, we wish to make inference about the locations of one or more changepoints of the sequence. We consider the Bayesian nonparameteric inference for multiple changepoint problem using a Bayesian segmentation procedure proposed by Yang and Kuo (2000). A mixture of products of Dirichlet process is used as a prior distribution. To decide whether there exists a single change or not, our approach depends on nonparametric Bayesian Schwartz information criterion at each step. We discuss how to choose the precision parameter (total mass parameter) in nonparametric setting and show that the discreteness of the Dirichlet process prior can ha17e a large effect on the nonparametric Bayesian Schwartz information criterion and leads to conclusions that are very different results from reasonable parametric model. One example is proposed to show this effect.

• Journal of the Korean Data and Information Science Society
• /
• 제10권2호
• /
• pp.319-327
• /
• 1999

영과잉-포아송분포는 여러 형태의 불량률을 줄이는 생산공정과정에서 유용하게 이용되어 왔다. 또한 생산공정과정 중 미지의 변화시점 이후 불량률의 변화가 있는지를 알아보는 것은 흥미 있는 일이고 연구된바있다. 만약 불량품들이 서로 두가지 다른 형태의 규격에 의해 발생되었다면, 이는 일변량이 아닌 이변량 영과잉-포아송 분포를 이용해야 할 것이다. 본 논문은 이변량 영과잉-포아송모형에서 어느 미지의 시점 이후 분포의 변화가 있는지를 우도비 검정을 통해 알아본다. 또한 변화가 있다면 변화시점과 그리고 여러 형태의 모수들에 대한 점추정량을 알아보려 한다.

• Communications for Statistical Applications and Methods
• /
• 제12권2호
• /
• pp.483-496
• /
• 2005

We consider the power law process which is assumed to have multiple changepoints. We propose a binary segmentation procedure for locating all existing changepoints. We select one model between the no-changepoints model and the single changepoint model by the Bayes factor. We repeat this procedure until no more changepoints are found. Then we carry out a multiple test based on the Bayes factor through the intrinsic priors of Berger and Pericchi (1996) to investigate the system behaviour of failure times. We demonstrate our procedure with a real dataset and some simulated datasets.

• 대한한방내과학회지
• /
• 제42권6호
• /
• pp.1255-1268
• /
• 2021

Objectives: This study aimed to analyze the healthcare utilization behavior of patients visiting the department of Korean internal medicine in the Korean medicine hospital of Wonkwang University in Jeon-ju from July 2018 to June 2021. Methods: We retrospectively analyzed the medical records of 26,108 patients and sorted the data by period, month, visiting types, new or returning types, sex, and age group. IBM SPSS 26.0 and the R 4.05 'changepoint' package were used with various statistical methods, such as Independent t-test, Mann-Whitney test, Chi-square test, Simple regression analysis. The P-value was set at 0.05. Results and Conclusions: Females outnumbered males regardless of period, and the ratio of females fell after COVID-19. Regardless of visiting types, patients in their 50s, 60s, and 70s outrated any other age group. The average number of females among the returning patients decreased significantly after COVID-19, but did not in males. Outpatients under 10 and in their 10s decreased significantly after COVID-19, as did inpatients in their 40s and 60s. The average duration of hospitalization was extended significantly after COVID-19. The number of outpatients and inpatients decreased as time passed after COVID-19. We expect that the results of this study will be used as reference materials in analyzing the effects of COVID-19 on healthcare utilization.