• 응용통계연구
• /
• 제27권1호
• /
• pp.21-30
• /
• 2014

치유율 모형(cure rate model)은 위험 그룹의 단조 감소에 대한 가정이 부적절한 경우에 적용될 수 있다. 예를 들어, 생존 분석에서 위험 그룹은 시간이 경과함에 따라 점점 감소하여 무한대의 시간대에는 영으로 수렴하며 이는 곧 생존 함수가 영으로 수렴함을 의미한다. 하지만 이러한 가정이 적합하지 못한 자료가 의약학, 사회학, 경제학 등에서 종종 발생된다. 즉, 어느 시점에 이르러 더 이상의 생존함수는 감소하지 않고 평행선을 보여주는 경우에 로그 순위검정(log rank test)과 Cox's 비례위험모형(proportional hazard model)의 적용은 바람직하지 못한 결론을 가져오게 된다. 이러한 자료에 대해 치유율 모형(cure rate model)에서는 사건 발생 취약 그룹(susceptible group)과 비취약 그룹(insusceptible group)으로 나누어 취약그룹에 대해서만 일반적인 생존 분석 방법을 적용하는 혼합 모형(mixture model)을 적용해왔다 (Berkson과 Gage, 1952). 본 연구에서는 이러한 치유율 모형을 군집화 구간 중도 절단 자료(clustered interval censored data)에 적용해 보고자 한다. 최근에 Kim과 Jhun (2008)은 구간 중도 절단자료에 대해 치유율 모형을 적용하였으며 본 연구에서는 그들의 방법을 군집화 자료로 확장할 것이다. 실제 자료 분석의 예로 금연자료를 분석할 것이다.

• 운동영양학회지
• /
• 제23권2호
• /
• pp.45-50
• /
• 2019

[Purpose] The purpose of this study was to confirm that the difference in excess post-exercise oxygen consumption (EPOC) during exercise of the spending the same calories between the continuous and interval exercise. [Methods] Thirty-four healthy college students who did not regularly exercise volunteered to participate in our study. Continuous exercise was performed on an ergometer for 30 min at 60% of maximal oxygen consumption (VO_{2 max}). Interval exercise was performed on a cycle ergometer at 80% VO_{2 max} for 2 min initially, followed by 40% VO_{2 max} for 1 min, and 80% VO_{2 max} for 3 min. This was repeated six times for a total of 26 min. [Results] The major findings were as follows: (1) energy consumption during exercise was not significantly different between continuous exercise and interval exercise groups; (2) EPOC was higher in interval exercise than in continuous exercise for all dependent variables (i.e., total oxygen consumption, total calories, summation of heart rate); and (3) there were no significant differences in the lipid profile between continuous and interval groups. [Conclusions] Our study confirmed that after equalizing energy expenditure for continuous and interval exercise on a cycle ergometer in subjects in their twenties, interval exercise results in higher EPOC than continuous exercise. These data suggest that interval exercise may be more effective than continuous exercise in reducing body fat, for a given amount of energy expenditure.

• Journal of the Korean Data and Information Science Society
• /
• 제4권
• /
• pp.31-44
• /
• 1993

Multivariate exponentially weighted moving average (EWMA) control charts for monitoring the variance-covariance matrix are investigated. A variable sampling interval (VSI) feature is considered in these charts. Multivariate EWMA control charts for monitoring the variance-covariance matrix are compared on the basis of their average time to signal (ATS) performances. The numerical results show that multivariate VSI EWMA control charts are more efficient than corrsponding multivariate fixed sampling interval (FSI) EWMA control charts.

• Journal of the Korean Data and Information Science Society
• /
• 제7권1호
• /
• pp.93-104
• /
• 1996

In this paper, Marshall and Olkin's bivariate exponential distribution is assumed for stress and strength model. We derive the asymptotic distributions and construct some approximate confidence intervals for P(X

• Journal of the Korean Data and Information Science Society
• /
• 제8권2호
• /
• pp.271-276
• /
• 1997

A dynamic discount approach is proposed for the estimation of the Poisson parameter and the forecasting of the Poisson random variable, where the parameter of the Poisson distribution varies over time intervals. The recursive estimation procedure of the Poisson parameter is provided. Also the forecasted distribution of the Poisson random variable in the next time interval based on the information gathered until the current time interval is provided.

• Journal of the Korean Data and Information Science Society
• /
• 제13권2호
• /
• pp.329-340
• /
• 2002

Two methods are proposed for constructing a confidence interval on the among group variance component in a unbalanced one-way random effects model. Computer simulation is used to compare these methods with alternative procedures. The results indicate that the method1 and methods2 perform well over small group size and large sample size respectively.

• Journal of the Korean Data and Information Science Society
• /
• 제14권4호
• /
• pp.989-995
• /
• 2003

Inference for probability P(Y

• Journal of the Korean Data and Information Science Society
• /
• 제21권4호
• /
• pp.819-829
• /
• 2010

Properties of multivariate variable sampling interval (VSI) Shewhart and CUSUM charts for monitoring mean vector of related quality variables are investigated. To evaluate average time to signal (ATS) and average number of switches (ANSW) of the proposed charts, Markov chain approaches and simulations are applied. Performances of the proposed charts are also investigated both when the process is in-control and when it is out-of-control.

• Journal of the Korean Data and Information Science Society
• /
• 제15권4호
• /
• pp.1003-1010
• /
• 2004

Properties of the variable sampling interval(VSI) CUSUM chart for monitoring dispersion matrix of related quality characteristics are investigated. Performances of the proposed charts are evaluated for matched fixed sampling interval(FSI) and VSI charts in terms of average time to signal(ATS) and average number of samples to signal (ANSS). Average number of swiches(ANSW) of the proposed VSI Shewhart and CUSUM charts are also investigated.

• 품질경영학회지
• /
• 제25권4호
• /
• pp.79-87
• /
• 1997

In this paper, we obtain maximum likelihood estimator(MLE) of a parallel system reliability for the Marshall and Olkin's bivariate exponential model with birariate type 1 consored data. The asymptotic normal distribution of the estimator is obtained. Also we construct an a, pp.oximate confidence interval for the reliability based on MLE. We present a numerical study for obtaining MLE and a, pp.oximate confidence interval of the reliability.