• Communications for Statistical Applications and Methods
• /
• v.15 no.1
• /
• pp.43-50
• /
• 2008

Multinomial logistic regression is a well known multiclass classification method in the field of statistical learning. More recently, the development of sparse multinomial logistic regression model has found application in microarray classification, where explicit identification of the most informative observations is of value. In this paper, we propose a sparse multinomial kernel logistic regression model, in which the sparsity arises from the use of a Laplacian prior and a fast exact algorithm is derived by employing a bound optimization approach. Experimental results are then presented to indicate the performance of the proposed procedure.

• The Korean Journal of Applied Statistics
• /
• v.22 no.3
• /
• pp.531-539
• /
• 2009

Logistic regression is widely used as a datamining technique for the customer relationship management. The maximum likelihood estimator has highly inflated variance when multicollinearity exists among the regressors, and it is not robust against outliers. Thus we propose the robust principal components logistic regression to deal with both multicollinearity and outlier problem. A procedure is suggested for the selection of principal components, which is based on the condition index. When a condition index is larger than the cutoff value obtained from the model constructed on the basis of the conjoint analysis, the corresponding principal component is removed from the logistic model. In addition, we employ an algorithm for the robust estimation, which strives to dampen the effect of outliers by applying the appropriate weights and factors to the leverage points and vertical outliers identified by the V-mask type criterion. The Monte Carlo simulation results indicate that the proposed procedure yields higher rate of correct classification than the existing method.

• Journal of Korean Institute of Industrial Engineers
• /
• v.27 no.4
• /
• pp.366-373
• /
• 2001

Economic component screening procedures for multi-component assembly products supplied with warranty are proposed. It is assumed that the screening variable is continuous and the performance variable is dichotomous. Logistic and normal models are considered; the proportion of conforming items is a logistic function of the screening variable in the logistic model and the screening variable given the performance variable is normally distributed in the normal model. Cost models are constructed which involve three cost components; screening inspection cost for each component, cost due to disposing a rejected component, and warranty cost for an assembly product. Methods of finding the optimal screening procedures are presented and numerical examples are given.

• Communications for Statistical Applications and Methods
• /
• v.14 no.3
• /
• pp.507-516
• /
• 2007

Multinomial logistic regression is probably the most popular representative of probabilistic discriminative classifiers for multiclass classification problems. In this paper, a kernel variant of multinomial logistic regression is proposed by combining a Newton's method with a bound optimization approach. This formulation allows us to apply highly efficient approximation methods that effectively overcomes conceptual and numerical problems of standard multiclass kernel classifiers. We also provide the approximate cross validation (ACV) method for choosing the hyperparameters which affect the performance of the proposed approach. Experimental results are then presented to indicate the performance of the proposed procedure.

• Journal of the Korean Data and Information Science Society
• /
• v.23 no.2
• /
• pp.385-392
• /
• 2012

Logistic regression is a well known binary classification method in the field of statistical learning. Mixed-effect regression models are widely used for the analysis of correlated data such as those found in longitudinal studies. We consider kernel extensions with semiparametric fixed effects and parametric random effects for the logistic regression. The estimation is performed through the penalized likelihood method based on kernel trick, and our focus is on the efficient computation and the effective hyperparameter selection. For the selection of optimal hyperparameters, cross-validation techniques are employed. Numerical results are then presented to indicate the performance of the proposed procedure.

• Journal of the East Asian Society of Dietary Life
• /
• v.16 no.4
• /
• pp.488-495
• /
• 2006

The purposes of this study were to measure respondent's demographic characteristics, respondent's attitudes toward chicken meat, and factors influencing the level of perceived helpfulness of country of origin in predicting the safety of chicken. The data was collected through a consumer survey during the March 2006. Two hundred fifty meat consumers living in Suncheon, the eastern part of Chonnam, were randomly selected as respondents. Eleven respondents did not complete the survey instrument, resulting in a final sample size of 239. All estimations were carried out using correlation, logistic procedure of SAS package, and plum procedure of SPSS. The level of perceived helpfulness of country of origin in predicting the safety of chicken meat was significantly correlated with trust, antibiotics and salmonella/bacteria among the attitude variables. The proportional odds assumption of the model was violated at p<0.05. The estimated results of the multinomial logit model indicated that income, single, occupation, and education significantly affected helpful perception over not helpful perception, while gender and occupation significantly affected very helpful perception over not helpful perception in the case of the extended model. These study results from this study could be useful in developing marketing and health promotion strategies, as well as government trade policy.

• Journal of the Korean Statistical Society
• /
• v.32 no.3
• /
• pp.299-309
• /
• 2003

Let ${\pi}_1,...,{\pi}_{k}$k($\geq$2) independent logistic populations such that the cumulative distribution function (cdf) of an observation from the population ${\pi}_{i}$ is $$F_{i}\;=\; {\frac{1}{1+exp{-\pi(x-{\mu}_{i})/(\sigma\sqrt{3})}}},\;$\mid$x$\mid$<\;{\infty}$$ where ${\mu}_{i}(-{\infty}\; < \; {\mu}_{i}\; <\; {\infty}$ is unknown location mean and ${\delta}^2$ is known variance, i ＝ 1,..., $textsc{k}$. Let ${\mu}_{[k]}$ be the largest of all ${\mu}$'s and the population ${\pi}_{i}$ is defined to be 'good' if ${\mu}_{i}\;{\geq}\;{\mu}_{[k]}\;-\;{\delta}_1$, where ${\delta}_1\;>\;0$, i = 1,...,$textsc{k}$. A selection procedure based on sample median is proposed to select a subset of $textsc{k}$ logistic populations which includes all the good populations with probability at least $P^{*}$(a preassigned value). Simultaneous confidence intervals for the differences of location parameters, which can be derived with the help of proposed procedures, are discussed. If a population with location parameter ${\mu}_{i}\;<\;{\mu}_{[k]}\;-\;{\delta}_2({\delta}_2\;>{\delta}_1)$, i ＝ 1,...,$textsc{k}$ is considered 'bad', a selection procedure is proposed so that the probability of either selecting a bad population or omitting a good population is at most 1­ $P^{*}$.

• Korean Journal of Biological Psychiatry
• /
• v.12 no.2
• /
• pp.165-172
• /
• 2005

Objectives:The purpose of this study is to 1) conduct a discrimination analysis of schizophrenia and bipolar affective disorder using MMPI profile through artificial neural network analysis and logistic regression analysis, 2) to make a comparison between advantages and disadvantages of the two methods, and 3) to demonstrate the usefulness of artificial neural network analysis of psychiatric data. Procedure:The MMPI profiles for 181 schizophrenia and bipolar affective disorder patients were selected. Of these profiles, 50 were randomly placed in the learning group and the remaining 131 were placed in the validation group. The artificial neural network was trained using the profiles of the learning group and the 131 profiles of the validation group were analyzed. A logistic regression analysis was then conducted in a similar manner. The results of the two analyses were compared and contrasted using sensitivity, specificity, ROC curves, and kappa index. Results:Logistic regression analysis and artificial neural network analysis both exhibited satisfactory discriminating ability at Kappa index of greater than 0.4. The comparison of the two methods revealed artificial neural network analysis is superior to logistic regression analysis in its discriminating capacity, displaying higher values of Kappa index, specificity, and AUC(Area Under the Curve) of ROC curve than those of logistic regression analysis. Conclusion:Artificial neural network analysis is a new tool whose frequency of use has been increasing for its superiority in nonlinear applications. However, it does possess insufficiencies such as difficulties in understanding the relationship between dependent and independent variables. Nevertheless, when used in conjunction with other analysis tools which supplement it, such as the logistic regression analysis, it may serve as a powerful tool for psychiatric data analysis.

• Journal of Information Technology Applications and Management
• /
• v.21 no.4_spc
• /
• pp.403-414
• /
• 2014

Forecasting technology in economic activity is a quite intricate procedure so researchers should grasp the point of the data to use. Diffusion models have been widely used for forecasting market demand and measuring the degree of technology diffusion. However, there is a question that a model, explaining a certain market with goodness of fit, always shows good performance with markets of different conditions. The primary aim of this paper is to explore diffusion models which are frequently used by researchers, and to help readers better understanding on those models. In this study, Logistic, Gompertz and Bass models are used for forecasting Global Wireline Subscribers and the performance of models is measured by Mean Absolute Percentage Error. Logistic model shows better MAPE than the other two. A possible extension of this study may verify which model reflects characteristics of industry better.

• Communications for Statistical Applications and Methods
• /
• v.18 no.5
• /
• pp.645-655
• /
• 2011

Chandrasekar et al. (2004) introduced a generalized Type-II hybrid censoring. In this paper, we propose generalized doubly Type-II hybrid censoring. In addition, this paper presents the statistical inference on the scale parameter for the half logistic distribution when samples are generalized doubly Type-II hybrid censoring. The approximate maximum likelihood(AMLE) method is developed to estimate the unknown parameter. The scale parameter is estimated by the AMLE method using two di erent Taylor series expansion types. We compar the AMLEs in the sense of the mean square error(MSE). The simulation procedure is repeated 10,000 times for the sample size n = 20; 30; 40 and various censored samples. The $AMLE_I$ is better than $AMLE_{II}$ in the sense of the MSE.