• Journal of the Korean Data and Information Science Society
• /
• v.28 no.5
• /
• pp.1021-1026
• /
• 2017

Mixture experiments are commonly encountered in many fields including food, chemical and pharmaceutical industries. In mixture experiments, measured response depends on the proportions of the components present in the mixture and not on the amount of the mixture. Statistical analysis of the data from mixture experiments has mainly focused on a continuous response variable. In the example of quantal response data in mixture experiments, however, the tumor incidence data have been analyzed in Chen et al. (1996) to study the effects of 3 dietary components on the expression of mammary gland tumor. In this paper, we compared the logistic regression models with linear predictors such as second degree Scheffe polynomial model, Becker model and Akay model in terms of classification accuracy.

• The Korean Journal of Applied Statistics
• /
• v.29 no.4
• /
• pp.595-611
• /
• 2016

We use nonlinear regression models (such as the Hill Model) when we analyze data in toxicology and/or pharmacology. In nonlinear regression models an estimator of parameters and estimation of measurement about uncertainty of the estimator are influenced by the variance structure of the error. Thus, estimation methods should be different depending on whether the data are homoscedastic or heteroscedastic. However, we do not know the variance structure of the error until we actually analyze the data. Therefore, developing estimation methods robust to the variance structure of the error is an important problem. In this paper we propose a method to estimate parameters in nonlinear regression models based on a preliminary test. We define an estimator which uses either the ordinary least square estimation method or the iterative weighted least square estimation method according to the results of a simple preliminary test for the equality of the error variance. The performance of the proposed estimator is compared to those of existing estimators by simulation studies. We also compare estimation methods using real data obtained from the National Toxicology program of the United States.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.5
• /
• pp.971-980
• /
• 2017

The varying coefficient regression model has gained lots of attention since it is capable to model dynamic changes of regression coefficients in many regression problems of science. In this paper we propose a varying coefficient regression model that effectively considers the errors on both input and response variables, which utilizes the kernel method in estimating the varying coefficient which is the unknown nonlinear function of smoothing variables. We provide a generalized cross validation method for choosing the hyper-parameters which affect the performance of the proposed model. The proposed method is evaluated through numerical studies.

• The Korean Journal of Applied Statistics
• /
• v.33 no.5
• /
• pp.569-578
• /
• 2020

By estimating conditional quantile functions of the response, quantile regression (QR) can provide comprehensive information of the relationship between the response and the predictors. In addition, kernel quantile regression (KQR) estimates a nonlinear conditional quantile function in reproducing kernel Hilbert spaces generated by a positive definite kernel function. However, it is infeasible to use the KQR in analysing a massive data due to the limitations of computer primary memory. We propose a divide and conquer based KQR (DC-KQR) method to overcome such a limitation. The proposed DC-KQR divides the entire data into a few subsets, then applies the KQR onto each subsets and derives a final estimator by aggregating all results from subsets. Simulation studies are presented to demonstrate the satisfactory performance of the proposed method.

• The Korean Journal of Applied Statistics
• /
• v.31 no.4
• /
• pp.475-484
• /
• 2018

Gamma generalized linear models are useful for non-negative and skewed responses. However, these models have received less attention than Poisson and binomial generalized linear models. In particular, hypothesis testing for the significance of regression coefficients has not been thoroughly studied. In this paper we assess the performance of various test statistics for gamma generalized linear models based on numerical studies. Our results show that the likelihood ratio test and F-type test are generally recommended and that the partial deviance test should be avoided in practice.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2009.05a
• /
• pp.74-78
• /
• 2009

우리 사회가 발전함에 따라 재해의 위험으로부터도 안전하게 살고자 하는 대중들의 욕구 또한 증가하고 있다. 하지만 최근의 기후변화와 이상홍수의 사례에서 볼 때 현재 우리가 처해 있는 자연재해로부터의 위협은 과거와는 상이하다는 것을 알 수 있다. 이러한 위협에 대처하기 위해서는 우리에게 노출된 재해의 특성을 평가하는 과정이 무엇보다 선행되어져야 한다. 홍수로 인한 피해는 대부분이 인명이나 재산피해가 주를 이루기 때문에 홍수위험도의 평가결과도 발생 가능한 인명이나 재산피해로 표현되는 것이 적절하다고 판단된다. 따라서 본 연구에서는 지역회귀분석을 적용하여 가능 홍수 피해금액을 추산하고, 이를 통해 각 지역별 홍수위험도를 평가하는 방법을 제안하였다. 지역회귀분석은 강우유출모형이나 확률분포모형의 매개변수들을 유역 특성인자들로 표현하기 위해 수문학 분야에서 사용되어져 왔으며 본 연구에서는 이 방법을 홍수 피해금액 추정에 응용하였다. 지역회귀방법의 절차는 먼저 계측지역에서는 홍수 피해금액과 시강우량 자료를 바탕으로 비선형회귀분석을 실시한 후 이 회귀식의 계수를 다시 해당 지역의 인문 사회 경제학적 인자들로 표현하였다. 이러한 방법을 통해 지역적 인자들이 홍수 피해에 미치는 영향을 정량적으로 분석할 수 있었으며 궁극적으로 미계측지역에서도 지역적 인자들을 통해 특정 빈도에 발생 가능한 홍수 피해금액을 추정할 수 있었다. 최종적으로 추정된 홍수 피해금액과 지역 총 자산의 비를 통해 홍수위험지도를 작성하였다. 본 연구결과를 수자원장기종합계획에서 홍수위험도 평가를 위해 사용된 홍수피해잠재능(Potential Flood Damage; PFD)과 비교해 보면 PFD에서는 각 인자들의 가중치 산정에서 전문가의 주관이 개입될 수 있다는 단점이 있었으나 과거 피해금액과의 상관관계를 분석한 본 연구에서는 이러한 단점을 극복할 수 있었다.

• Journal of the Korean Geotechnical Society
• /
• v.19 no.6
• /
• pp.371-378
• /
• 2003

The compression index of clay distributed in the west and south coast of the Korean Peninsula had been studied. Compression index was obtained from the conventional consolidation test, and was conducted accordingly to obtain the field virgin compression curve by means of Schmertmann's graphical correction. To examine a correlation closely between physical properties of soils($e_o$, LL, w) and compression index(Cc), linen. and non-linear regression analysis were employed based on the data collected from tests. The conclusions are as follows. The compression index obtained by means of Schmereann's graphical correction is about 1.16 times for the value of original oedometer test curve for U/D samples. Non-liner regression curve was preferable to establish a correlation equation rather than linear regression curve. All derived equations so far achieved have been summarized and given. However, linear equation is better for practical use so that part by part simplified linear equations were also suggested alternatively together with their own non-linear regression curve.

• Communications for Statistical Applications and Methods
• /
• v.15 no.1
• /
• pp.27-41
• /
• 2008

A graphical method of checking the adequacy of a generalized linear model is proposed. The graph helps to assess the assumption that the link function of mean can be expressed as a linear combination of explanatory variables in the generalized linear model. For the graph the boosting technique is applied to estimate nonparametrically the relationship between the link function of the mean and the explanatory variables, though any other nonparametric regression methods can be applied. Through simulation studies with normal and binary data, the effectiveness of the graph is demonstrated. And we list some limitations and technical details of the graph.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.3B
• /
• pp.279-289
• /
• 2006

The reconstruction of low dimension nonlinear behavior from the hydrologic time series has been an active area of research in the last decade. In this study, we present the applications of a powerful state space reconstruction methodology using the method of Support Vector Machines (SVM) to the Great Salt Lake (GSL) volume. SVMs are machine learning systems that use a hypothesis space of linear functions in a Kernel induced higher dimensional feature space. SVMs are optimized by minimizing a bound on a generalized error (risk) measure, rather than just the mean square error over a training set. The utility of this SVM regression approach is demonstrated through applications to the short term forecasts of the biweekly GSL volume. The SVM based reconstruction is used to develop time series forecasts for multiple lead times ranging from the period of two weeks to several months. The reliability of the algorithm in learning and forecasting the dynamics is tested using split sample sensitivity analyses, with a particular interest in forecasting extreme states. Unlike previously reported methodologies, SVMs are able to extract the dynamics using only a few past observed data points (Support Vectors, SV) out of the training examples. Considering statistical measures, the prediction model based on SVM demonstrated encouraging and promising results in a short-term prediction. Thus, the SVM method presented in this study suggests a competitive methodology for the forecast of hydrologic time series.

• Journal of Korean Society of Transportation
• /
• v.26 no.1
• /
• pp.113-126
• /
• 2008

This research aims to explore the effects of multicollinearity on the reliability and goodness of fit of logit model. To investigate the effects of multicollinearity on the multinominal logit model, numerical experiments are performed. The exploratory variables(attributes of utility functions) which have a certain degree of correlations from (rho=) 0.0 to (rho=) 0.9 are generated and rho-squares and t-statistics which are the indices of goodness of fit and reliability of logit model are traced. From the well designed numerical experiments, following findings are validated : 1) When a new exploratory variable is added, some of rho-squares increase while the others decrease. 2) The higher relations between generic variables lead a logit model worse with respect to goodness of fit. 3) Multicollinearity has a tendency to produce over-evaluated parameters. 4) The reliability of the estimated parameter has a tendency to decrease when the correlations between attributes are high. These results suggest that we have to examine the existence of multicollinearity and perform the proper treatments to diminish multicollinearity when we develop logit model.