• The Korean Journal of Applied Statistics
• /
• v.26 no.3
• /
• pp.511-520
• /
• 2013

Detection outliers and robust estimators are crucial in regression models with outliers. In such studies the focus is on detecting outliers and estimating the coefficients using leave-one-out. Our study introduces Rice estimator which is an error variance estimator without estimating the coefficients. In particular, we study a comparison of the statistical properties for Rice estimator with and without outliers in simple regression models.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.2
• /
• pp.305-315
• /
• 2014

In a simple linear regression, a linear relationship between an explanatory variable and a response variable can be easily recognized in the scatter plot of them. The lack of fit test for the replicated data is commonly used for testing the linearity but it is not easy to test the linearity when the explanatory variable is not replicated. In this paper, we propose three new test statistics for testing the linearity regardless of replication using the principle of average slope and validate them through several simulations and empirical studies.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.2
• /
• pp.251-260
• /
• 2009

In this study, we propose a new estimation method based on autocovariance for selecting optimal estimators of the regression coefficients in the simple linear regression model. Although this method does not seem to be intuitively attractive, these estimators are unbiased for the corresponding regression coefficients. When the exploratory variable takes the equally spaced values between 0 and 1, under mild conditions which are satisfied when errors follow an autoregressive moving average model, we show that these estimators have asymptotically the same distributions as the least squares estimators. Additionally, under the same conditions as before, we provide a self-contained proof that these estimators converge in probability to the corresponding regression coefficients.

• Proceedings of the KIPE Conference
• /
• 2018.07a
• /
• pp.246-248
• /
• 2018

본 논문에서는 배터리 수명의 지표인 SOH(state of health) 추정 시 배터리 노화에 따라 방전 용량의 급격한 변화가 발생하면 SOH도 변화하게 된다. 이로 인해 잘못된 SOH의 정보를 가지고 오게 되며 배터리의 안정성 및 신뢰성에 문제가 된다. 본 논문에서는 방전 용량과 내부 저항의 선형적 관계를 확인하고, 방전 용량과 내부저항을 고려한 단순선형회귀모형(simple linear regression model)을 모델링하였다. 방전 용량의 급격한 변화나 오프라인 기반 방전 용량을 측정함에 어려움이 있는 경우 단순선형회귀모형에 따라 방전 용량을 추정하여 SOH를 보정하는 기법을 제안하고 이에 대한 검증을 수행하였다.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.6
• /
• pp.1491-1498
• /
• 2014

The major criticism of optimal experimental design is that it depends heavily on the model and its accompanying assumption that often leads the number of support points equal to the number of parameters in the model. Often in the past, a polynomial model of higher degree is assumed to handle the experimental design for the polynomial regression of lower degree. In this paper we searched the possible set of designs which are robust to the departure of the assumed model. The designs are categorized with respect to D-efficiency. The approach by O'Brien (1995) was discussed in univariate polynomial regression model setting.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.6
• /
• pp.876-880
• /
• 2008

Outliers are the observations which are very larger or smaller than most observations in the given data set. These are shown by some sources. The result of the analysis with outliers may be depended on them. In general, we do data analysis after removing outliers. But, in data mining applications such as fraud detection and intrusion detection, outliers are included in training data because they have crucial information. In regression models, simple and multiple regression models need to eliminate outliers from given training data by standadized and studentized residuals to construct good model. In this paper, we use support vector regression(SVR) based on statistical teaming theory to analyze data with outliers in regression. We verify the improved performance of our work by the experiment using synthetic data sets.

• Proceedings of the Korean Society of Disaster Information Conference
• /
• 2016.11a
• /
• pp.207-211
• /
• 2016

최근 세계적으로 기후변화에 따라 자연재해에 의한 피해가 대형화, 가속화 되면서 이를 예측하고 대응할 수 있는 체계적이며 국내 특성을 반영할 수 있는 피해예측 시스템의 필요성이 제기되고 있다. 국내에서는 경험적 통계기반의 강우예측에 대한 연구가 주로 진행되었으며, 강풍에 대한 연구는 부족한 상황이다. 본 연구는 기존의 연구와는 달리 모델링을 통한 예측이 아닌 실제 발생한 강풍 피해 자료를 기반으로 풍속에 따른 피해액을 예측할 수 있는 강풍 피해예측 단순회귀모형을 개발하는 것을 목적으로 한다.

• Water for future
• /
• v.17 no.2
• /
• pp.107-112
• /
• 1984

It si presented here that in order to estimate reservoir sedimentation rate through the use of reservoir survey data of 66 irrigation reservoir in 3 major watersheds in this country, the correlation between reservoir sedimentation rate and the following factors; watershed area, trap-efficiency, watershed slope, shape factor of water shed, and reservoir deposition age in two models simple regression model and multiple regression model. Appropriatness of the proposed models have been calibrated from the survey data and as a result, it has been determined that the multiple regression model is much more accurate than the simple regression model. The annual sediment yield is correlated with watershed area and reservoir trap efficiency. It has been found that variation of the annual average sedimentation rate and the annual reservoir capacity loss rate are influenced by the trap efficiency of reservoir.

• The Korean Journal of Applied Statistics
• /
• v.26 no.6
• /
• pp.953-958
• /
• 2013

This study suggests a measurement error model based on skewed normal distribution instead of normal distribution to identify slope parameter properties in a simple liner regression model. We prove that the slope parameter in a simple linear regression model is underestimated.

• Electronics and Telecommunications Trends
• /
• v.17 no.3 s.75
• /
• pp.80-86
• /
• 2002

본 연구는 현재 통신서비스 산업에서 가장 많이 사용하고 있는 5개 예측모형(단순 성장 모형, 단순 Logistic 모형, Gompertz 모형, 확장 Bass 모형, 시간 변동 Bass 모형)을 이용한 초고속 인터넷 가입자에 대한 예측력을 비교 평가하는 데 있다. 예측모형의 추정 방법으로 비선형 회귀방정식(nonlinear regression)을 사용하여 추정의 효율성을 높였다. 예측력 비교분석 기준은 (i) 포화점에 대한 타당성 (ii) 모수에 대한 통계적 유의성 (iii) 실제치 대비 예측치에 대한 AAD 기준을 통하여 예측모형의 예측력을 비교 평가하였다. 본 연구에서 실시한 방법론에 따라 다섯 가지 통신서비스 예측모형의 예측력을 분석한 결과 가장 작은 AAD를 나타낸 예측모형은 Log-Logistic 모형으로 나타났으며, 가장 큰 AAD를 나타낸 예측모형은 단순 Logistic 모형으로 나타났다. 또한 AAD 기준에서 보면 일반적으로 많이 사용하고 있는 Gompertz 예측모형과 Bass 모형 중에서는 Gompertz 예측모형이 더 우월한 것으로 나타났다.