• Communications for Statistical Applications and Methods
• /
• 제26권3호
• /
• pp.273-293
• /
• 2019

We consider the problem of model selection in multiple linear regression with outliers and non-normal error distributions. In this article, the robust model selection criterion is proposed based on the robust estimation method with the least absolute deviation (LAD). The proposed criterion is shown to be consistent. We suggest proposed criterion based algorithms that are suitable for a large number of predictors in the model. These algorithms select only relevant predictor variables with probability one for large sample sizes. An exhaustive simulation study shows that the criterion performs well. However, the proposed criterion is applied to a real data set to examine its applicability. The simulation results show the proficiency of algorithms in the presence of outliers, non-normal distribution, and multicollinearity.

• Journal of the Korean Statistical Society
• /
• 제21권1호
• /
• pp.1-13
• /
• 1992

This article deals with variable selection problem under a newly formed predictive heteroscedastic discriminant rule that accounts for mulitple homogeneous covariance matrices across the K multivariate normal populations. A general version of predictive discriminant rule, a variable selection criterion, and a criterion for stopping with further selection are suggested. In a simulation study the practical utilities of those considered are demonstrated.

• 국제학술발표논문집
• /
• The 3th International Conference on Construction Engineering and Project Management
• /
• pp.1564-1569
• /
• 2009

Project managers play a key role in cost, time, and quality of a project. Selection of an appropriate project manager, therefore, is considered as one of the most important decisions in any construction project. It should be noted that most important decision makings are carried out by the project manager throughout the project. Traditionally, project manager selection in construction companies in Iran is through organizing an interview with candidates and selecting the most appropriate choice in accordance with the capabilities, potentials and individual specifications coupled with the requirements of the project. In the same direction, organizing interview on selection of appropriate candidate is usually carried out by senior managers of companies. Determination of the most important criteria for selection of project managers and also identification of significance coefficient of each criterion can highly help senior managers of companies to make sound selection decisions. In this paper, a numerical model has been considered for determination of significance of each criterion, details of which are submitted for selection of project manager in Iranian petrochemical, oil and gas sector companies. For this reason, all criteria- considered by senior managers of the companies under study- are first determined. Then, information obtained through 38 interviews, conducted by senior managers of the mentioned companies while selecting project manager, is analyzed. Significant coefficient of each criterion is calculated through the accumulated data using fuzzy curves method.

• 비파괴검사학회지
• /
• 제21권1호
• /
• pp.46-53
• /
• 2001

음향방출 신호를 이용하여 분류기를 설계하는 과정에서의 특징값 선택법에 관해 연구하였다. 분류기는 역전파법을 이용한 신경망 분류기를 사용하였다. Fisher's criterion, class mean scatter criterion, eigenvector analysis와 함께 본 논문에서 새로 제안하는 특징값 공간에서의 특징값 좌표사이의 차이를 이용하는 2-D criterion, 3-D criterion을 이용해서 특징값을 선택하고 각각에 대해 분류기를 설계하여, 인식률과 수렴속도를 비교하였다. 분류를 위한 자료를 얻기 위하여 용접부 결함시편과 로터리 압축기 금속 접촉부 결함시편을 사용하였다. 인식률 면에서 2-D criterion과 3-D criterion이 우수한 결과를 나타내었다.

• 한국항공운항학회지
• /
• 제14권4호
• /
• pp.101-109
• /
• 2006

This study investigates what criterion airline customers recognize important when evaluating airline firms. Specifically it is surveyed if different criterion are used by different groups of airline customers when choosing an airline firm. In addition customer group with high loyalty to 'K' airline, national carrier of Korea, is differently evaluate 'K' airline for the selection criterion over customer group without loyalty. Frequent flyer program is suggested most important by most of the customers being followed by flight schedule. Flight schedule, in-flight food and air fare of 'K' airline are differently evaluated according to level of royalty to the airline. However there appears no difference in the evaluation of seat and entertainment between two groups, customers with high loyalty and customers without loyalty.

• 반도체디스플레이기술학회지
• /
• 제14권2호
• /
• pp.9-16
• /
• 2015

In this paper, selection criterions on selection diversity are researched. The diversity is applied to the multiple antenna system based on wireless access in vehicular environment (WAVE) standard for rapid varying channel. Least squares (LS) based decision feedback equalizer (DFE) are used for channel equalization. Received signal is regenerated by means of the decision feedback path. In the selection diversity, the regenerated signal as well as the received signal is selected according to selection criterion. The decision feedback algorithm can follow the fast speed of WAVE fading channel. To control the tracking speed of the time-varying channel, simple low pass filter is used. Finally, the estimated channel value recovers the distorted payloads. Signal power before automatic gain control (AGC) in analog stage can be used as a selection criterion. In the digital stage, signal power after AGC, noise power after AGC, signal to noise ratio after AGC and cross-correlation method can be used as selection criterions. According to the simulation results, the performance of the selection diversity is improved in comparison with that of the combining diversity for the WAVE fading channel.

• 응용통계연구
• /
• 제22권1호
• /
• pp.197-204
• /
• 2009

In the model selection problem, the main objective is to choose the true model from a manageable set of candidate models. An information criterion gauges the validity of a statistical model and judges the balance between goodness-of-fit and parsimony; "how well observed values ran approximate to the true values" and "how much information can be explained by the lower dimensional model" In this study, we introduce some information criteria modified from the Akaike Information Criterion (AIC) and the Bayesian Information Criterion(BIC). The information criteria considered in this study are compared via simulation studies and real application.

• 응용통계연구
• /
• 제11권2호
• /
• pp.435-449
• /
• 1998

본 연구는 다중판별분석(MDA)에서 필요한 변수선택기준을 베이즈접근법으로 제안하였다. 이 베이즈판별변수 선택기준은 여러 정규모집단분포의 평균벡터에 대한 동질성 검정에 필요한 디폴터형태의 베이즈요인을 객관적 베이즈방법으로 유도하여 설정하였다. 디폴트베이즈요인(default Bayes factor)은 Spiegelhalter와 Smith (1982)가 계발한 가상적트레이닝표본법(imaginary training sample method)을 사용하여서 도출하였다. 또한 제안된 베이즈판별변수선택 기준이 지닌 분포의 성질을 이용하여, 추가 판별변수(또는 변수군)가 MDA에 기여하는 부가적인 판별력에 대한 검정법 및 추가판별변수(또는 변수군)의 선택 기준에 대해서도 논하였다. 본 연구에서 새로이 얻은 변수선택기준은 최적부분집합선택법(optimal subset selection method)뿐 아니라 각 단계적방법(stepwise method)의 변수선택기준으로 사용될 수 있으며, 두 그룹 판별분석에도 사용이 가능하다는 점에서 표본이론에 의해 여러 형태로 개발된 기존의 판별변수 선택 기준들을 하나로 통합시킬 수 있는 기능을 지니고 있다. 모의실험을 실시하여 최적 부분집합선택법과 단계적방법하에서 제안된 판별변수선택 기준이 가진 효용성을 평가하였다.

• 컴퓨터교육학회논문지
• /
• 제22권5호
• /
• pp.39-50
• /
• 2019

본 연구에서는 중학교 SW교육에 활용할 수 있는 피지컬 컴퓨팅 교구의 선정을 위한 기준을 개발하였다. 교구를 선정하기 위한 기준을 개발하기 위하여 문헌 분석, 델파이 설문 실시와 AHP 방법을 적용하였다. 먼저 문헌을 통해 피지컬 컴퓨팅 교구가 갖추어야 할 특성을 '교육과정 적합성', '안전성', '내구성', '경제성', '범용성', '매력성', '관리의 용이성' 7개의 영역으로 설정하고 전문가 델파이 설문을 통해 영역별 세부 기준을 도출하여 7개 영역의 31개 세부 기준으로 구성된 피지컬 컴퓨팅 교구의 선정 기준을 제안하였다. 이렇게 제안된 선정 기준에 대해 추가로 AHP 방법을 적용하여 7개의 영역과 31개의 세부 기준에 대한 상대적 중요도를 분석하고 이를 바탕으로 세부 기준별 배점을 계산하여 정량화된 피지컬 컴퓨팅 교구의 선정 기준을 개발하였다.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제2권1호
• /
• pp.41-60
• /
• 1998

This paper derives a consistent and bias corrected extension of Akaike's Information Criterion (AIC), $AIC_{bc}$, based on Kullback-Leibler information. This criterion has terms that penalize the overparametrization more strongly for small and large samples than that of AIC. The overfitting problem of the asymptotically efficient model selection criteria for small and large samples will be overcome. The $AIC_{bc}$ also provides a consistent model order selection. Thus, it is widely applicable to data with small and/or large sample sizes, and to cases where the number of free parameters is a relatively large fraction of the sample size. Relationships with other model selection criteria such as $AIC_c$ of Hurvich, CAICF of Bozdogan and etc. are discussed. Empirical performances of the $AIC_{bc}$ are studied and discussed in better model order choices of a linear regression model using a Monte Carlo experiment.