• 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.

• 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.

• Communications for Statistical Applications and Methods
• /
• v.26 no.6
• /
• pp.557-573
• /
• 2019

Mortality study is an essential component of actuarial risk management for life insurance policies, annuities, and pension plans. Life expectancy has drastically increased over the last several decades; consequently, longevity risk associated with annuity products and pension systems has emerged as a crucial issue. Among the various aspects of mortality study, a consideration of the cause-of-death mortality can provide a more comprehensive understanding of the nature of mortality/longevity risk. In this case study, the cause-of-mortality data in Korea and the US were analyzed along with a multinomial logistic regression model that was constructed to quantify the impact of mortality reduction in a specific cause on actuarial values. The results of analyses imply that mortality improvement due to a specific cause should be carefully monitored and reflected in mortality/longevity risk management. It was also confirmed that multinomial logistic regression model is a useful tool for analyzing cause-of-death mortality for actuarial applications.

• Communications for Statistical Applications and Methods
• /
• v.27 no.1
• /
• pp.129-140
• /
• 2020

In this paper, we introduce an efficient algorithm for the non-convex penalized multinomial logistic regression that can be uniformly applied to a class of non-convex penalties. The class includes most non-convex penalties such as the smoothly clipped absolute deviation, minimax concave and bridge penalties. The algorithm is developed based on the concave-convex procedure and modified local quadratic approximation algorithm. However, usual quadratic approximation may slow down computational speed since the dimension of the Hessian matrix depends on the number of categories of the output variable. For this issue, we use a uniform bound of the Hessian matrix in the quadratic approximation. The algorithm is available from the R package ncpen developed by the authors. Numerical studies via simulations and real data sets are provided for illustration.

• Journal of the Semiconductor & Display Technology
• /
• v.18 no.4
• /
• pp.110-115
• /
• 2019

Blur detection and segmentation play vital role in many computer vision applications. Among various methods, local binary pattern based methods provide reasonable blur detection results. However, in conventional local binary pattern based methods, the blur map is computed by using a fixed threshold irrespective of the type and level of blur. It may not be suitable for images with variations in imaging conditions and blur. In this paper we propose an effective method based on local binary pattern with adaptive threshold for blur detection. The adaptive threshold is computed based on the model learned through the multinomial logistic regression. The performance of the proposed method is evaluated using different datasets. The comparative analysis not only demonstrates the effectiveness of the proposed method but also exhibits it superiority over the existing methods.

• Communications for Statistical Applications and Methods
• /
• v.26 no.5
• /
• pp.507-517
• /
• 2019

Statistical matching is a method of combining multiple sources of data that are extracted or surveyed from the same population. It can be used in situation when variables of interest are not jointly observed. It is a low-cost way to expect high-effects in terms of being able to create synthetic data using existing sources. In this paper, we propose the several statistical micro matching methods using a multinomial logistic regression model when all variables of interest are categorical or categorized ones, which is common in sample survey. Under conditional independence assumption (CIA), a mixed statistical matching method, which is useful when auxiliary information is not available, is proposed. We also propose a statistical matching method with auxiliary information that reduces the bias of the conventional matching methods suggested under CIA. Through a simulation study, proposed micro matching methods and conventional ones are compared. Simulation study shows that suggested matching methods outperform the existing ones especially when CIA does not hold.

• The Korean Journal of Applied Statistics
• /
• v.21 no.4
• /
• pp.589-602
• /
• 2008

This article studies on disability pensioners' characteristic with multinomial logit and logistic regression model. Seven factors are examined on whether each factor is reflected in degree of disability in the disability pension. By incorporating multinomial logit and logistic regression model, effectiveness and characteristic of the seven factors are investigated on the degree of disability. Result shows all the seven factors are significant on the degree of disability, while among the seven, five factors, age, sex, type of coverage, type of category, insured duration show a trend in degree of disability and the other two, cause of disability and class of standard monthly income are not effective on trend in degree of disability. Results from analyses might be useful for disability pension management.

• Journal of Preventive Veterinary Medicine
• /
• v.41 no.3
• /
• pp.129-132
• /
• 2017

The current study identified risk factors associated with porcine circovirus type 2 (PCV2) infection on pig farms in the Republic of Korea using a multinomial logistic regression model to evaluate the PCV2 infection status of pigs at different growth stages. Compulsory disinfection of visitors (odds ratio [OR]: 0.019, 95% confidence interval [CI]: <0.001-0.378, p=0.0095), compulsory registration of visitors (OR: 0.002, 95% CI: <0.001-0.184, p=0.0070), regular blood testing (OR: 0.012, 95% CI: <0.001-0.157, p=0.0007), and running on-farm biosecurity learning programs for workers (OR: 0.156, 95% CI: 0.040-0.604, p=0.0072 and OR: 0.201, 95% CI: 0.055-0.737, p=0.0155, respectively) were identified as factors which could reduce the risk of PCV2 infection. However, visitation by a regular veterinarian (OR: 32.733, 95% CI: 3.768-284.327, p=0.0016) was associated with PCV2 infection.

• Communications for Statistical Applications and Methods
• /
• v.12 no.2
• /
• pp.313-322
• /
• 2005

In this paper, we discuss suppression for logistic regression model. Suppression for linear regression model was defined as the relationship among sums of squared for regression as well as correlation coefficients of. variables. Since it is not common to obtain simple correlation coefficient for binary response variable of logistic model, we consider cumulative logistic models with multinomial and ordinal response variables rather than usual logistic model. As number of category of a response variable for the cumulative logistic model gets collapsed into binary, it is found that suppressions for these logistic models are changed. These suppression results for cumulative logistic models are discussed and compared with those of linear model.

• The Journal of Engineering Geology
• /
• v.31 no.1
• /
• pp.31-42
• /
• 2021

Database of Cut-slope management system (CSMS) has been constructed based on investigations of all slopes on the roads of the whole country. The investigation data is documented by human, so it is inevitable to avoid human-error such as missing-data and incorrect entering data into computer. The goal of this paper is constructing a prediction model based on several machine-learning algorithms to solve those imperfection problems of the CSMS data. First of all, the character-type data in CSMS data must be transformed to numeric data. After then, two algorithms, i.g., multinomial logistic regression and deep-neural-network (DNN), are performed, and those prediction models from two algorithms are compared. Finally, it is identified that the accuracy of DNN-model is better than logistic model, and the DNN-model will be utilized to improve data-quality.