• Journal of the Korean Statistical Society
• /
• 제25권1호
• /
• pp.133-144
• /
• 1996

We, in this paper, propose a nonparametric estimator of bivariate mean residual life function based on Lin and Ying's (1993) bivariate survival function estimator of paired failure times under univariate censoring and prove the uniform consistency and the weak convergence result of this estimator. Through Monte Carlo simulation, the performances of the proposed estimator are tabulated and are illustrated with the skin grafts data.

• 응용통계연구
• /
• 제25권4호
• /
• pp.605-612
• /
• 2012

Multivariate data are often generated with multiple outcomes in various fields. Multiple outcomes could be mixed as continuous and discrete. Because of their complexity, the data are often dealt with by separately applying regression analysis to each outcome even though they are associated the each other. This univariate approach results in the low efficiency of estimates for parameters. We study the efficiency gains of the multivariate approaches relative to the univariate approach with the mixed data that include continuous and binary outcomes. All approaches yield consistent estimates for parameters with complete data. By jointly estimating parameters using multivariate methods, it is generally possible to obtain more accurate estimates for parameters than by a univariate approach. The association between continuous and binary outcomes creates a gap in efficiency between multivariate and univariate approaches. We provide a guidance to analyze the mixed data.

• 한국품질경영학회:학술대회논문집
• /
• 한국품질경영학회 2006년도 추계 학술대회
• /
• pp.221-226
• /
• 2006

We usually use two techniques(influence function and local influence) for detecting outliers. But, we cannot use these difficult techniques in elementary industrial statistics course for college students. We can use some simple graphical methods(box plot, dandelion seed plot, influence graph and cumulative deletion plot) for univariate and bivariate outlier detection and outlier effect in elementary industrial statistics course for college students.

• 응용통계연구
• /
• 제35권3호
• /
• pp.385-393
• /
• 2022

본 논문에서는 시계열 예측 분야에서 잘 알려져 있는 단변량 시계열 모형들을 이용하여, 그들의 단순 조합이 어떤 예측력을 보여주는지 연구한다. 고려된 단변량 시계열 모형으로는, 지수평활 및 ARIMA(autoregressive integrated moving average) 모형들과 그들의 확장된 형태인 모형들 그리고 예측의 벤치마크 모형으로 자주 사용되는 비계절 및 계절 랜덤워크 모형이다. 단순 조합의 방법은 중앙값과 평균을 이용하였으며, 검증을 위하여 사용된 데이터셋은 3,003개의 시계열 자료로 구성된 M3-competition 자료이다. 예측 성능을 sMAPE(symmetric mean absolute percentage error)와 MASE(mean absolute scaled error)로 평가한 결과, 단변량 시계열 모형들의 단순 조합이 아주 우수한 예측력을 가지고 있음을 확인하였다.

• 응용통계연구
• /
• 제28권3호
• /
• pp.541-559
• /
• 2015

VaR는 금융위험을 측정하고 관리하기위한 중요한 도구로 현재 널리 사용되고 있다. 특히 금융자산 수익률의 변동성에 적합한 모형을 찾는 것은 VaR의 정확한 측정을 위해 중요한 과제이다. 본 연구에서는 한국의 코스피, 중국의 항셍, 일본의 니케이지수들로 구성된 포트폴리오의 VaR를 측정하기 위한 변동성모형으로 다양한 일변량모형들과 다변량모형들을 함께 고려하여 그 성과를 비교하였다. 사후검증을 통해 전체적으로 일변량모형들보다는 다변량모형들이 VaR의 측정에 더 적합한 것으로 보여 졌으며 특히 DCC와 ADCC모형이 더욱 우수한 것으로 나타났다.

• Journal of applied mathematics & informatics
• /
• 제18권1_2호
• /
• pp.247-259
• /
• 2005

Necessary and sufficient conditions, under which there exists (at least) a sequence of vectors of real numbers for which the distribution function (d.f.) of any vector of extreme order statistics converges to a non-degenerate limit, are derived. The interesting thing is that these conditions solely depend on the univariate marginals. Moreover, the limit splits into the product of the limit univariate marginals if all the bivariate marginals of the trivariate d.f., from which the sample is drawn, is of negative quadrant dependent random variables (r.v.'s). Finally, all these results are stated for the multivariate extremes with arbitrary dimensions.

• 응용통계연구
• /
• 제22권5호
• /
• pp.1007-1017
• /
• 2009

본 연구는 최근에 활발히 연구가 진행 중인 항공수요 예측 분야에서 사용되는 계절형 ARIMA 모형과 다변량 계절형 시계열 모형과의 성능을 비교한 것이다. 본 연구에서는 국제 여객 수요와 국제 화물 수요 예측을 위하여 실제 자료를 이용하여 비교한 결과 다변량 계절형 시계열 모형이 예측의 정확도 면에서 기존의 일변량 모형보다 우수함을 보였다.

• 충청수학회지
• /
• 제29권3호
• /
• pp.385-396
• /
• 2016

Characterizations of probability distributions by different regression conditions on generalized order statistics has attracted the attention of many researchers. We present here, characterization of Pareto and Weibull distributions based on the conditional expectation of generalized order statistics extending the characterization results reported by Jin and Lee (2014). We also present a characterization of the power function distribution based on the conditional expectation of lower generalized order statistics.

• Journal of the Korean Data and Information Science Society
• /
• 제25권6호
• /
• pp.1591-1598
• /
• 2014

The reviews of the balance sheet of commercial banks showed that loan item constitutes the largest portion of bank's assets. Although the sector has highest rate of profit, it possesses the greatest risk. Identifying factors that can contribute in lifting-up the loan repayment rate of customers of Hawassa district commercial bank is the major goal of this study. A sample of 183 customers who took loan from October, 2005 to April, 2012 was taken from the bank record. Kaplan-Meier estimation method and univariate Cox proportional hazard model were applied to identify factors affecting bank loan repayment rate. The result from Kaplan-Meier survival estimation revealed that the loan repayment rate is significantly related with loan type, and previous loan experience, educational level and mode of repayment. The log-rank test indicates that the survival probability of loan customers is not statistically different in repaying the loan among groups classified by sex. Moreover, the univariate Cox proportional hazard model result portrayed that educational level, having previous loan experience, mode of repayment, collateral type and purpose of loan are significantly related with loan repayment rate of customers commercial bank. Hence, banks should design loan strategies giving special emphasis on the significant factors while they are giving loans to their customers.

• 지질공학
• /
• 제24권2호
• /
• pp.191-199
• /
• 2014

We describe a method for detecting slope instability in flume tests using pore pressure and water content data in conjunction with a statistical control chart analysis. Specifically, we conducted univariate statistical analysis on x-MR control chart data (pore pressure and water content) collected at several points along the flume slope, which we separated into three parts: upper, middle, and lower. To assess our results in the context of landslide forecasting and warning systems, we applied control limit lines at $1{\sigma}$, $2{\sigma}$, and $3{\sigma}$ levels of uncertainty. In doing so, we observed that dispersion time varies depending on the control limit line used. Moreover, the detection of instabilities is highly dependent on the position and type of sensor. Our findings indicate that different characteristics of the data on various factors predict slope failure differently and these characteristics can be identified by univariate statistical analysis. Therefore, we suggest that a univariate statistical approach is an effective method for the early detection of slope instability.