• Journal of the Korean Data and Information Science Society
• /
• 제22권1호
• /
• pp.107-113
• /
• 2011

We present methods for studying the log-density ratio, which allow us to select which predictors are needed, and how they should be included in the logistic regression model. Under multivariate normal distributional assumptions, we investigate the form of the log-density ratio as a function of many predictors. The linear, quadratic and crossproduct terms are required in general. If two covariance matrices are equal, then the crossproduct and quadratic terms are not needed. If the variables are uncorrelated, we do not need the crossproduct terms, but we still need the linear and quadratic terms.

• Communications for Statistical Applications and Methods
• /
• 제8권1호
• /
• pp.291-297
• /
• 2001

For a stochastic regression model in which the errors are assumed to form a stationary linear process, we show that the difference between the empirical distribution functions of the errors and the estimates of those errors converges uniformly in probability to zero at the rate of $o_{p}$ ( $n^{-}$$\frac{1}{2}$) as the sample size n increases.

• Journal of the Korean Data and Information Science Society
• /
• 제16권2호
• /
• pp.445-449
• /
• 2005

Yen et al. [Fuzzy Sets and Systems 106 (1999) 167-177] calculated the fuzzy membership function for the output to find the non-symmetric triangular fuzzy number coefficients of a linear regression model for all given input-output data sets. In this note, we show that the result they obtained in their paper is invalid.

• Journal of the Korean Data and Information Science Society
• /
• 제16권4호
• /
• pp.1087-1094
• /
• 2005

e-insensitive support vector regression(e-SVR) is capable of providing more complete description of the linear and nonlinear relationships among random variables. In this paper we propose an iterative reweighted least squares(IRWLS) procedure to solve the quadratic problem of e-SVR with a modified loss function. Furthermore, we introduce the generalized approximate cross validation function to select the hyperparameters which affect the performance of e-SVR. Experimental results are then presented which illustrate the performance of the IRWLS procedure for e-SVR.

• 정보처리학회논문지D
• /
• 제11D권1호
• /
• pp.163-172
• /
• 2004

객체지향 개발 방법론을 적용하는 소프트웨어 개발 프로젝트에서 개발 노력 추정 기법으로 사용사례점수(UCP, Use Case Point)에 대한 연구가 계속되고 있다. 기존의 연구는 기술적 요인과 환경적 요인을 적용한 AUCP(Adjusted Use Case Point)에 상수를 곱하여 개발 노력을 계산하는 선형모델을 제시하고 있으나, AUCP와 UUCP(Unadjusted Use Case Point)를 이용하여 개발노력을 추정하는 통계적인 모델은 제시되지 않고 있다. 소프트웨어 규모가 증가함에 따라 개발 기간이 기하급수적으로 증가하는 선형 회귀모델이 부적합하다는 사실과 UCP 계산과정에서 TCF(Technical Complexity Factor)와 EF(Environmental Factor)를 적용에 따른 FP(Function Point) 오차 발생 문제점을 확인하였다. 이 논문은 사용사례점수를 기반으로 하여 기존 연구의 문제점인 TCF와 EF를 고려하지 않고 직접 UUCP로부터 개발 노력을 추정한 수 있는 선형, 로그형, 다항식, 거듭제곱 및 지수함수 회귀모델의 성능을 평가한 결과, 가장 적합한 모델로 지수형태의 비선형 회귀모델을 도출하였다.

• Journal of the Korean Data and Information Science Society
• /
• 제25권3호
• /
• pp.677-684
• /
• 2014

Support vector quantile regression (SVQR) is capable of providing more complete description of the linear and nonlinear relationships among random variables. To improve the estimation performance of SVQR we propose to use SVQR ensemble with bagging (bootstrap aggregating), in which SVQRs are trained independently using the training data sets sampled randomly via a bootstrap method. Then, they are aggregated to obtain the estimator of the quantile regression function using the penalized objective function composed of check functions. Experimental results are then presented, which illustrate the performance of SVQR ensemble with bagging.

• Journal of the Korean Data and Information Science Society
• /
• 제15권2호
• /
• pp.449-455
• /
• 2004

Support vector machine (SVM) has been very successful in pattern recognition and function estimation problems for crisp data. This paper proposes a new method to evaluate interval regression models for crisp input-output data. The proposed method is based on quadratic loss SVM, which implements quadratic programming approach giving more diverse spread coefficients than a linear programming one. The proposed algorithm here is model-free method in the sense that we do not have to assume the underlying model function. Experimental result is then presented which indicate the performance of this algorithm.

• 대한수의학회지
• /
• 제50권1호
• /
• pp.11-17
• /
• 2010

Linear and non-linear regressions were used to derive the calibration function for the measurement of roxithromycin plasma concentration. Their results were compared with weighted least squares regression by usual weight factors. In this paper the performance of a non-linear calibration equation with the capacity to account empirically for the curvature, y = ax$^{b}$ + c (b $\neq$ 1) is compared with the commonly used linear equation, y = ax + b, as well as the quadratic equation, y = ax$^{2}$+ bx + c. In the calibration curve (range of 0.01 to 10 ${\mu}g/mL$) of roxithromycin, both heteroscedasticity and nonlinearity were present therefore linear least squares regression methods could result in large errors in the determination of roxithromycin concentration. By the non-linear and weighted least squares regression, the accuracy of the analytical method was improved at the lower end of the calibration curve. This study suggests that the non-linear calibration equation should be considered when a curve is required to be fitted to low dose calibration data which exhibit slight curvature.

• 한국안전학회지
• /
• 제35권5호
• /
• pp.15-21
• /
• 2020

Quantitative risk assessment (QRA) is used as a legal or voluntary safety management tool for the hazardous material industry and the utilization of the method is gradually increasing. Therefore, a leak frequency analysis based on reliable generic data is a critical element in the evolution of QRA and safety technologies. The aim of this paper is to derive the leak frequency function that can be applied more flexibly in QRA based on OGP report with high reliability and global utilization. For the purpose, we first reviewed the data on the 16 equipments included in the OGP report and selected the predictors. And then we found good equations to fit the OGP data using non-linear regression analysis. The various expectation functions were applied to search for suitable parameter to serve as a meaningful reference in the future. The results of this analysis show that the best fitting parameter is found in the form of DNV function and connection function in natural logarithm. In conclusion, the average percentage error between the fitted and the original value is very small as 3 %, so the derived prediction function can be applicable in the quantitative frequency analysis. This study is to contribute to expand the applicability of QRA and advance safety engineering as providing the generic equations for practical leak frequency analysis.

• 응용통계연구
• /
• 제18권3호
• /
• pp.543-553
• /
• 2005

선형 로지스틱 모형은 신용위험 관리를 위한 신용평점 모형 구축에 있어서 널리 쓰이고 있는 방법론이다. 본 논문에서는 신용평점화를 위하여 로지스틱 회귀 방법에 기초한 스플라인 방법론을 다루고자 한다. 선형 스플라인과 자동적인 변수선택 방법을 채택하였다. 모의 실험을 통하여 스플라인 방법의 성능을 규명하였다.