• The Korean Journal of Applied Statistics
• /
• v.29 no.2
• /
• pp.309-319
• /
• 2016

For binary classification models, we consider a risk score that is a function of linear scores and estimate the coefficients of the linear scores. There are two estimation methods: one is to obtain MLEs using logistic models and the other is to estimate by maximizing AUC. AUC approach estimates are better than MLEs when using logistic models under a general situation which does not support logistic assumptions. This paper considers imbalanced data that contains a smaller number of observations in the default class than those in the non-default for credit assessment models; consequently, the AUC approach is applied to imbalanced data. Various logit link functions are used as a link function to generate imbalanced data. It is found that predicted coefficients obtained by the AUC approach are equivalent to (or better) than those from logistic models for low default probability - imbalanced data.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.56 no.4
• /
• pp.29-39
• /
• 2014

In this study, we performed a non-stationary frequency analysis using a power model and the model was applied for Seoul, Daegu, Daejeon, Mokpo sites in Korea to estimate the probable precipitation amount at the target years (2020, 2050, 2080). We used the annual maximum precipitation of 24 hours duration of precipitation using data from 1973 to 2009. We compared results to that of non-stationary analyses using the linear and logistic regression. The probable precipitation amounts using linear regression showed very large increase in the long term projection, while the logistic regression resulted in similar amounts for different target years because the logistic function converges before 2020. But the probable precipitation amount for the target years using a power model showed reasonable results suggesting that power model be able to reflect the increase of hydrologic extremes reasonably well.

• Communications for Statistical Applications and Methods
• /
• v.15 no.6
• /
• pp.815-823
• /
• 2008

In this paper, we derive the approximate maximum likelihood estimators(AMLEs) and maximum likelihood estimator of the scale parameter in a half-logistic distribution based on progressive Type-II censored samples. We compare the proposed estimators in the sense of the mean squared error for various censored samples. We also obtain the approximate maximum likelihood estimators of the reliability function using the proposed estimators. We compare the proposed estimators in the sense of the mean squared error.

• Journal of the Korean Data and Information Science Society
• /
• v.18 no.4
• /
• pp.1081-1091
• /
• 2007

In this paper, we derive the approximate maximum likelihood estimators of the scale parameter and location parameter in an exponentiated logistic distribution based on multiply Type-II censored samples. We compare the proposed estimators in the sense of the mean squared error for various censored samples. We also propose and compare the estimators of the reliability function by using the proposed estimators of the parameters.

• Journal of the Chungcheong Mathematical Society
• /
• v.26 no.3
• /
• pp.441-451
• /
• 2013

In this paper, we derive recurrence relations for moments of lower generalized order statistics within a class of doubly truncated distributions. Inverse Weibull, exponentiated Weibull, power function, exponentiated Pareto, exponentiated gamma, generalized exponential, exponentiated log-logistic, generalized inverse Weibull, extended type I generalized logistic, logistic and Gumble distributions are given as illustrative examples. Further, recurrence relations for moments of order statistics and lower record values are obtained as special cases of the lower generalized order statistics, also two theorems for characterizing the general form of distribution based on single moments of lower generalized order statistics are given.

• Proceedings of the Korean Statistical Society Conference
• /
• 2005.11a
• /
• pp.181-186
• /
• 2005

Many data sets obtained from surveys or medical trials often include missing observations. When these data sets are analyzed, it is general to use only complete cases. However, it is possible to have big biases or involve inefficiency. In this paper, we consider a method for estimating parameters in logistic linear models involving non-ignorable missing data mechanism. A binomial response and normal exploratory model for the missing data are used. We fit the model using the EM algorithm. The E-step is derived by Metropolis-hastings algorithm to generate a sample for missing data and Monte-carlo technique, and the M-step is by Newton-Raphson to maximize likelihood function. Asymptotic variances of the MLE's are derived and the standard error and estimates of parameters are compared.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2000.11a
• /
• pp.417-426
• /
• 2000

This study suggests integrated neural network models for Interest rate forecasting using change-point detection, classifiers, and classification functions based on structural change. The proposed model is composed of three phases with tee-staged learning. The first phase is to detect successive and appropriate structural changes in interest rare dataset. The second phase is to forecast change-point group with classifiers (discriminant analysis, logistic regression, and backpropagation neural networks) and their. combined classification functions. The fecal phase is to forecast the interest rate with backpropagation neural networks. We propose some classification functions to overcome the problems of two-staged learning that cannot measure the performance of the first learning. Subsequently, we compare the structured models with a neural network model alone and, in addition, determine which of classifiers and classification functions can perform better. This article then examines the predictability of the proposed classification functions for interest rate forecasting using structural change.

• The Journal of Korean Society for School & Community Health Education
• /
• v.22 no.3
• /
• pp.83-96
• /
• 2021

Background & objectives: Cognitive function decline is a main factor influencing the overall life of the elderly and places a burden of society. The aime of this study was to investigate the risk factors of cognitive function decline of elderly living alone and living with a spouse. Methods: This study used the Korean Longitudinal Study of Ageing from 2014 to 2018. 243 older adults who lived alone and 1,155 lived with a spouse with the Korean version of Mini Mental State Examination scores in normal range at the time of 2014 were included in the analysis. Logistic regression analysis was conducted to determine the difference of risk factors affecting cognitive function decline between in elderly living alone and elderly living with a spouse. Results: Cognitive function decline incidence rate of elderly living alone was 30.5% and the elderly living with a spouse showed 23.0%. According to the results of logistic regression analysis, the risk factors of cognitive function decline in the elderly living alone was age and residential area, while in the elderly living with a spouse were age, education level, social networks, and depression. Conclusions: The factors that affect the cognitive function decline of the elderly living alone and the elderly living with a spouse were different. Accordingly, other measures to prevent cognitive decline are necessary.

• 한국노년학
• /
• v.39 no.2
• /
• pp.389-404
• /
• 2019

The present study aims to examine the relationship between self-reported sensory impairment and cognitive function among older adults in Korea. Drawn from the 2017 Survey of Living Conditions and Welfare Needs Korean Older Persons, a total of 10,082 adults aged 65 and over were included in analyses. Results from hierarchial multiple regression analysis show that those who reported greater subjective discomfort about vision, hearing, and oral function were more likely to have poor cognitive function. Results from hierarchial logistic regression analysis show. Results from logistic regression analysis show that having hearing and oral discomfort increased the a risk for dementia. Findings suggest that it is necessary to manage sensory function of the elderly at the government level and to develop self-evaluation tools to monitor changes in sensory function for older adults. Future research should target finding effective ways to improve health of older adults.

• Journal of the Korean Society of Physical Medicine
• /
• v.11 no.3
• /
• pp.73-80
• /
• 2016

PURPOSE: The purpose of this study was to investigate the quality of life related to fall experiences in chronic stroke patients. METHODS: This cross-sectional study included 117 patients with stroke from 3 hospitals in D metropolitan city. General characteristics, including fall experiences and quality of life, were assessed through a face-to-face interviews conducted in a quiet place using a questionnaire. Measurement of quality of life in stroke patients was conducted using the Korean Stroke Specific Quality of Life Scale (SS-QOL). To identify the SS-QOL items related to fall experiences, the items of the SS-QOL were considered as independent variables, and the variables that were significantly different according to fall experiences were identified using a univariate analysis. A binary logistic regression was then performed using fall experiences as the independent variable. RESULTS: According to the univariate analysis, self help activities, social role, and upper extremity function were significantly lower in the fall group than that in the non-fall group (p<.05). The findings of the binary logistic regression confirmed that social roles and upper extremity function were the SS-QOL items that were related to fall experience in chronic stroke patients. CONCLUSION: These findings suggest that social roles and upper extremity function may be risk factors for fall experience in patients with chronic stroke.