• 물과 미래
• /
• 제50권1호
• /
• pp.18-25
• /
• 2017

• 응용통계연구
• /
• 제29권6호
• /
• pp.1095-1106
• /
• 2016

Koenker 등 (1978)에 의해 제안 된 분위수 회귀분석법은 독립변수들이 주어졌을 때, 종속변수의 조건부 분위수에 초점을 맞추어 독립변수들과 종속변수의 해당 특정 분위수와의 관계를 분석하는 방법이다. 선형프로그래밍법 등을 이용한 분위수 회귀의 추정 과정을 생각해 볼 때, 고차원 대용량 자료의 경우에는 모형 적합에 어려움을 겪을 수 밖에 없다. 따라서 분위수 회귀의 문제에 있어서도 차원 축소의 문제, 조금 더 폭을 좁혀 생각해보면 변수선택의 문제를 통해 의사 결정에 영향을 미치는 주요 요인들을 파악하거나 적절한 규모의 모형을 적합하는 과정이 중요하다고 할 수 있다. 본 논문에서는 분위수 회귀의 변수선택의 문제를 보다 직관적이고 간단하게 해결하기 위한 방법으로서 회귀나무 모형을 응용하여 한국야구위원회에 등록된 선수들의 연봉과 기록 데이터를 분석해 보았다. 분석 결과, 각 분위수 별로 소수의 주요 변수가 선택되어 차원축소의 효과를 얻을 수 있었다. 또한 해당 분위수별로 선택된 변수도 해석상 의미 있는 것으로 평가할 수 있었다.

• 보건행정학회지
• /
• 제25권3호
• /
• pp.240-251
• /
• 2015

Background: Dentist's income is quite variable. We investigate the factors underlying the distribution of dental revenue and dentist income. Methods: Financial and structural variables of private dental practices(N=13,967) were examined with 2010 Economic Census microdata which include non-insurance revenue. We conducted quantile regression method(QRM) and ordinary least square(OLS) in treating skewness and heteroskedasticity of distributions. The effective estimation for the upper and lower range of distribution becomes possible by QRM. Results: Mid-career dentists are shown to have higher revenue and income. Male dentists achieve the higher revenue and income than female dentists in all quantiles. Group practices show lower income per owner than solo practices significantly. The revenue and income are increased with increasing size of clinics. The high cost in renting the clinic office is found to have a big positive effect on the revenue but a little positive effect on the income. Interestingly the density of dentists shows negative effect on the lowest quantile of the revenue but positive effect on the highest quantile. The lowest quantile of the revenue in the capital areas have the relatively high revenue. The lowest quantile of the income in metropolitan city show higher income than those in other areas significantly. Conclusion: The suggested QRM is shown to have more effective and efficient tool in finding out determinants of dentists' revenue and income of our concern. The results of this study are expected to be employed for dentists preparing for the opening practices in their organizational settings and locational selections. The distributional efficiency of dental human resources could be accomplished if policy makers guide dentists with this knowledge.

• Communications for Statistical Applications and Methods
• /
• 제3권3호
• /
• pp.179-186
• /
• 1996

Bioequivanence models arise typically in bioassays when new preparations are compared against standard ones by means of responses on some biological organisms. Relative potency measures provide nice interpretations for such bioequivalence and their estimation constitutes the prime interest of such studies. A conditional quantile process based on the k-nearest neighbor method is proposed for this purpose. An alternative procedure based on Kolmogrov-Smirnov type estimator has also been considered along with. ARIC ultrasound data are analyzed as examples.

• Communications for Statistical Applications and Methods
• /
• 제6권1호
• /
• pp.25-32
• /
• 1999

A single outlier can influence on the least squares estimators and can invalidate analysis based on these estimators. The Cook's statistic has been introduced to measure influence of individual data point on parameter estimation and the quantile of the F distribution is recommended as a reference value. but in practice subjective judgement is applied in the choice of appropriate quantile. A simple reference value is introduced in this paper which is developed by approximating conditional quantities of Cook's measure. The performance of the proposed criterion is evaluated through analysis of real data set.

• 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.

• 응용통계연구
• /
• 제25권1호
• /
• pp.197-203
• /
• 2012

In fitting a regression model, we often encounter data sets which do not follow Gaussian distribution and/or do not have equal variance. In this case estimation of the conditional density of a response variable at a given design point is hardly solved by a standard least squares method. To solve this problem, we propose a simple method to estimate the distribution of the fitted vales under heteroscedasticity using the idea of quantile regression and the histogram techniques. Application of this method to a real data sets is given.

• International Journal of Reliability and Applications
• /
• 제9권1호
• /
• pp.53-70
• /
• 2008

In this paper, we discuss the plethora of uses for the software package R, and focus specifically on its helpful applications in reliability data analyses. Examples are presented; including the R coding protocol, R code, and plots for various statistical as well as reliability analyses. We explore Kaplan-Meier estimates and maximum likelihood estimation for distributions including the Weibull. Finally, we discuss future applications of R, and usages of quantile regression in reliability.

• Communications for Statistical Applications and Methods
• /
• 제28권6호
• /
• pp.643-653
• /
• 2021

Few studies are found in literature on estimation of population quantiles using the method of ranked set sampling (RSS). The optimal RSS strategy is to select observations with at most two fixed rank order statistics from different ranked sets. In this paper, a near optimal unbalanced RSS model for estimating p^th(0 < p < 1) population quantile is proposed. Main advantage of this model is to use each rank order statistics and is distributionfree. The asymptotic relative efficiency (ARE) for balanced RSS, unbalanced optimal and proposed near-optimal methods are computed for different values of p. We also compared these AREs with respect to simple random sampling. The results show that proposed unbalanced RSS performs uniformly better than balanced RSS for all set sizes and is very close to the optimal RSS for large set sizes. For the practical utility, the near optimal unbalanced RSS is recommended for estimating the quantiles.

• Journal of the Korean Data and Information Science Society
• /
• 제20권6호
• /
• pp.1093-1101
• /
• 2009

분위수 회귀모형은 확률변수들 사이에 확률적인 관계구조를 포함한 함수 모형을 좀 더 완벽하게 추정하도록 제공한다. 본 논문에서는 함수 추정에 로버스트하다고 알려져 있는 서포트벡터기계 기법과 이중벌칙커널기계를 이용하여 분위수 회귀모형을 추정하고자 한다. 이중벌칙커널기계는 고차원의 입력변수에 대한 분위수 회귀가 요구될 때 분위수 회귀모형을 잘 추정한다고 알려져 있다. 또한 본 논문에서는 광범위한 형태의 분위수 회귀모형 추정을 위해서 정규분포보다 비대칭 라플라스 분포를 이용한다. 본 논문에서 제안한 모형은 분위수 회귀모형 추정을 위해서 서포트벡터기계 기법에 이중벌칙커널기계를 이용하여 각각의 평균과 분산을 동시에 추정한다. 평균과 분산함수 추정을 위해 사용된 커널함수의 모수들은 최적의 값을 찾기 위해 일반화근사 교차타당성을 이용한다.