• Communications for Statistical Applications and Methods
• /
• 제20권4호
• /
• pp.259-270
• /
• 2013

This paper considers a penalized composite quantile regression (CQR) that performs a variable selection in the linear model with grouped variables. An adaptive sup-norm penalized CQR (ASCQR) is proposed to select variables in a grouped manner; in addition, the consistency and oracle property of the resulting estimator are also derived under some regularity conditions. To improve the efficiency of estimation and variable selection, this paper suggests the two-stage penalized CQR (TSCQR), which uses the ASCQR to select relevant groups in the first stage and the adaptive lasso penalized CQR to select important variables in the second stage. Simulation studies are conducted to illustrate the finite sample performance of the proposed methods.

• Communications for Statistical Applications and Methods
• /
• 제14권3호
• /
• pp.609-621
• /
• 2007

Diagnostic test results, which are approximately normal with a few number of outliers, but non-normal probability distribution, are frequently observed in practice. In the evaluation of two diagnostic tests, Greenhouse and Mantel (1950) proposed a parametric test under the assumption of normality but this test is inappropriate for the above non-normal case. In this paper, we propose a computationally simple nonparametric test that is based on quantile estimators of mean and standard deviation, instead of the moment-based mean and standard deviation as in some parametric tests. Parametric and nonparametric tests are compared with simulations under the assumption of, respectively, normality and non-normality, and under various combinations of the probability distributions for the normal and diseased groups.

• 응용통계연구
• /
• 제33권5호
• /
• pp.569-578
• /
• 2020

분위수 회귀모형은 반응변수의 조건부 분위수 함수를 추정함으로써 반응변수와 예측변수의 관계에 대한 포괄적인 정보를 제공한다. 특히 커널 분위수 회귀모형은 비선형 관계식을 고려하기 위하여 양정치 커널함수(kernel function)에 의해 만들어지는 재생 커널 힐버트 공간(reproducing kernel Hilbert space)에서 비선형 조건부 분위수 함수를 추정한다. 그러나 KQR은 이차계획법으로 공식화되어 많은 계산비용을 필요로 하므로 컴퓨터 메모리 능력의 제한으로 대용량 자료의 분석은 불가능하다. 이러한 문제점을 해결하기 위하여 본 논문에서는 분할정복(divide and conquer) 알고리즘을 활용한 KQR 추정법(DC-KQR)을 제안한다. DC-KQR은 먼저 전체 훈련자료를 몇 개의 부분집합으로 무작위로 분할(divide)한 후, 각각의 부분집합에 대하여 KQR 분위수 함수를 추정하고 이들의 산술 평균을 이용하여 최종적인 추정량으로 통합(conquer)하는 기법이다. 본 논문에서는 모의실험과 실제자료 분석을 통해 제안한 DC-KQR의 효율적인 성능과 활용 가능성을 확인하였다.

• Communications for Statistical Applications and Methods
• /
• 제22권6호
• /
• pp.543-556
• /
• 2015

We present a survey of contributions that defined the nature and extent of robust statistics for the last 50 years. From the pioneering work of Tukey, Huber, and Hampel that focused on robust location parameter estimation, we presented various generalizations of these estimation procedures that cover a wide variety of models and data analysis methods. Among these extensions, we present linear models, clustered and dependent observations, times series data, binary and discrete data, models for spatial data, nonparametric methods, and forward search methods for outliers. We also present the current interest in robust statistics and conclude with suggestions on the possible future direction of this area for statistical science.

• Journal of the Korean Statistical Society
• /
• 제27권3호
• /
• pp.359-368
• /
• 1998

Let ξ$_{p}$(z$_{0}$) be the pth quantile of the distribution of the survival time of an individual with time-invariant covariate vector z$_{0}$ in the additive risk model. We propose an estimator of (ξ$_{p}$(z$_{0}$) and derive its asymptotic distribution, and then construct an approximate confidence interval of ξ$_{p}$(z$_{0}$) . Simulation studies are carried out to investigate performance of the proposed estimator far practical sample sizes in terms of empirical coverage probabilities. Also, the estimator is illustrated on small cell lung cancer data taken from Ying, Jung, and Wei (1995) .d Wei (1995) .

• 응용통계연구
• /
• 제25권1호
• /
• pp.101-114
• /
• 2012

자동차보험의 손해율이란 지급보험금의 수입보험료에 대한 비율을 의미한다. 손해율이 매우 큰 값을 갖는 대형손실이 일어나는 경우에는 보험회사의 재무적인 부분에 큰 악영향을 미치게 된다. 따라서 보험회사가 이에 대비할 수 있도록 하기 위하여 손해율의 극단 분위수(extreme quantile)를 추정하는 것은 매우 중요한 일이다. 다른 종류의 보험 관련 데이터와 같이 손해율의 분포는 오른쪽으로 긴 꼬리를 갖는 두꺼운 꼬리분포(heavy-tailed distribution)를 갖는다. 이런 자료에서 극단 분위수룰 추정하기 위하여 가장 많이 사용되는 방법론은 POT(Peaks over threshold)와 Hill 추정(Hill estimation)이다. 본 논문에서는 일반화파레토분포(generalized Pareto distribution; GPD)의 다양한 모수추정방법론의 성능을 모의실험과 실제 손해율 데이터를 사용하여 비교, 분석하였다. 또한 Hill 추정치를 사용하여 극단 분위수를 추정하였다. 그 결과 대부분의 경우에 POT 방법론이 Hill 추정치를 이용한 방법보다 정확한 분위수를 추정하였고, 모수추정방법론 중에서는 MLE, Zhang, NLS-2 방법론이 가장 좋은 결과를 보여주었다.

• Journal of the Korean Statistical Society
• /
• 제22권2호
• /
• pp.159-169
• /
• 1993

In this article, we consider two sample problem with randomly right censored data. We propse two-sample confidence intervals for the difference in medians or any quantiles, based on bootstrap. The bootstrap version of two-sample confidence intervals proposed in this article is simple to apply and do not need the assumption of the shift model, so that for the non-shift model, the density estimation is not necessary, which is an attractive feature in small to moderate sized sample case.

• 품질경영학회지
• /
• 제23권1호
• /
• pp.29-40
• /
• 1995

This paper considers the problem of optimally designing accelerated degradation tests in which the performance value of a specimen is measured only at one of three test conditions for a given exposure time. For the product having lognormally distributed performance, the optimum plan-low stress level and sample proportion allocated to each test condition - is obtained, which minimize the asymptotic variance of maximum likelihood estimator of a stated quantile at design stress. An illustrative example for the optimum plan is given.

• Communications for Statistical Applications and Methods
• /
• 제15권3호
• /
• pp.421-427
• /
• 2008

This paper deals with the problem of testing for the existence of change in mean and estimating the change-point when the data are from the exponential distributions. The likelihood ratio test statistic and Gombay and Horvath (1990) test statistic are compared in a power study when there exists one change-point in the exponential means. Also the change-point estimator using the likelihood ratio and the change-point estimators based on Gombay and Horvath (1990) statistic are compared for their detecting capability via simulation.

• 품질경영학회지
• /
• 제24권4호
• /
• pp.44-58
• /
• 1996

This paper presents optimal accelerated life test plans with different censoring times for exponential, Weibull, and lognormal lifetime distributions, respectively. For an optimal plan, low stress level, proportion of test units allocated and censoring time at each stress are determined such that the asymptotic variance of the maximum likelihood estimator of a certain quantile at use condition is minimized. The proposed plans are compared with the corresponding optimal plans with a common censoring time over range of parameter values. Computational results indicate that those plans are statistically optimal ones in terms of accuracy of estimator when total censoring times of two plans are equal.