• Journal of the Korean Data and Information Science Society
• /
• v.26 no.1
• /
• pp.141-150
• /
• 2015

Graphical paradigms for assessing the adequacy of models in logistic regression are discussed. The residual plot has been widely used as a graphical tool for evaluating the adequacy of the model. However, this approach works well only for linear models with constant variance, and the alternative approach, the marginal model plot, has its defects as well. We suggest a Chi-residual plot that overcomes the potential shortcomings of the marginal model plot.

• The Korean Journal of Applied Statistics
• /
• v.14 no.1
• /
• pp.71-80
• /
• 2001

Logistic regression model is one of the most popular linear models for a binary response variable and used for the estimation of probability function. In many practical situations, the probability function can be expressed by a bell shaped curve and such a function can be estimated by a second order logistic regression model. However, when the probability curve is asymmetric, the estimation results using a second order logistic regression model may not be precise because a second order logistic regression model is a symmetric function. In addition, even if a second order logistic regression model is used, the interpretation for the effect of second order term may not be easy. In this paper, in order to alleviate such problems, an estimation method for asymmetric probabiity curve based on a first order logistic regression model and iterative bi-section method is proposed and its performance is compared with that of a second order logistic regression model by a simulation study.

• International Journal of Highway Engineering
• /
• v.13 no.4
• /
• pp.199-209
• /
• 2011

In the study of traffic safety, the analysis on factors affecting crash severity and the understanding about their relationship is important to be planning and execute to improve safety of road and traffic facilities. The purpose of this study is to develop a hierarchical binomial logistic model to identify the significant factors affecting fatal injuries and vehicle damages of traffic crashes on freeway. Two models on death and total vehicle damage are developed. The hierarchical structure of response variable is composed of two level, crash-occupant and crash-vehicle. As a result, we have gotten the crash-level random effect from these hierarchical structure as well as the fixed effect of covariates, namely odds ratio. The crash on the main line and in-out section have greater damage than other facilities. Injuries and vehicle damages are severe in case of traffic violations, centerline invasion and speeding. Also, collision crash and fire occurrence is more severe damaged than other crash types. The surrounding environment of surface conditions by climate and visibility conditions by day and night is a significant factor on crash occurrence. On the orher hand, the geometric condition of road isn't.

• The Korean Journal of Applied Statistics
• /
• v.23 no.5
• /
• pp.857-870
• /
• 2010

This study was conducted to investigate the relationship between the socio-demographic factors and the Korean consumers palatability evaluation grades with Hanwoo sensory evaluation data from 2006 to 2008 by National Institute of Animal Science. The dichotomy logistic regression model and the multinomial logistic regression model are fitted with the independent variables such as the consumer living location, age, gender occupation, monthly income, beef cut and the the palatability grade as the categorical dependent variable and tenderness, 리avor and juiciness as the continuous dependent variable. Stepwise variable selection procedure is incorporated to find the final model and odds ratios are calculated to nd the associations between categories.

• 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 Data and Information Science Society
• /
• v.25 no.1
• /
• pp.177-185
• /
• 2014

Under bivariate normal distribution assumptions, the interaction and quadratic terms are needed in the logistic regression model with two predictors. However, depending on the correlation coefficient and the variances of two conditional distributions, the interaction and quadratic terms may not be necessary. Although the need for these terms can be determined by comparing the two scatter plots, it is not as useful for interaction terms. We explore the structure and usefulness of the 3-D residual plot as a tool for dealing with interaction in logistic regression models. If predictors have an interaction effect, a 3-D residual plot can show the effect. This is illustrated by simulated and real data.

• The Korean Journal of Applied Statistics
• /
• v.35 no.1
• /
• pp.131-146
• /
• 2022

Logit models are commonly used to predicting and classifying categorical response variables. Most Bayesian approaches to logit models are implemented based on the Metropolis-Hastings algorithm. However, the algorithm has disadvantages of slow convergence and difficulty in ensuring adequacy for the proposal distribution. Therefore, we use auxiliary mixture sampler proposed by Frühwirth-Schnatter and Frühwirth (2007) to estimate logit models. This method introduces two sequences of auxiliary latent variables to make logit models satisfy normality and linearity. As a result, the method leads that logit model can be easily implemented by Gibbs sampling. We applied the proposed method to diabetes data from the Community Health Survey (2020) of the Korea Disease Control and Prevention Agency and compared performance with Metropolis-Hastings algorithm. In addition, we showed that the logit model using auxiliary mixture sampling has a great classification performance comparable to that of the machine learning models.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.2
• /
• pp.403-410
• /
• 2014

Binary logistic regression analysis is a statistical technique that explains binary response variable by quantitative or qualitative explanatory variables. In the binary logistic regression model, the probability that the response variable equals, say 1, one of the binary values is to be explained as a transformation of linear combination of explanatory variables. This is one of big barriers that non-statisticians have to overcome in order to understand the model. In this study, an educational tool is developed that explains the need of the binary logistic regression analysis using Excel VBA. More precisely, this tool explains the problems related to modeling the probability of the response variable equal to 1 as a linear combination of explanatory variables and then shows how these problems can be solved through some transformations of the linear combination.

• The Korean Journal of Applied Statistics
• /
• v.27 no.1
• /
• pp.89-102
• /
• 2014

In this study, we analyze the effect on the smoking status in the Seoul Metropolitan area using a multilevel logistic model with Community Health Survey data from the Korea Centers for Disease Control and Prevention. Intraclass correlation coefficient (ICC), profiling analysis and two types of predicted value were used to determine the appropriate multilevel analysis level. Sensitivity, specificity, percentage of correctly classified observations (PCC) and ROC curve evaluated model performance. We showed the applicability for multilevel analysis allowed for the possibility that different factors contribute to within group and between group variability using survey data.

• Journal of the Korean Data and Information Science Society
• /
• v.23 no.2
• /
• pp.235-245
• /
• 2012

Logistic discrimination is an useful statistical technique for quantitative analysis of financial service industry. Especially it is not only easy to be implemented, but also has good classification rate. Generalized additive model is useful for credit scoring since it has the same advantages of logistic discrimination as well as accounting ability for the nonlinear effects of the explanatory variables. It may, however, need too many additive terms in the model when the number of explanatory variables is very large and there may exist dependencies among the variables. Mixtures of factor analyzers can be used for dimension reduction of high-dimensional feature. This study proposes to use the low-dimensional factor scores of mixtures of factor analyzers as the new features in the generalized additive model. Its application is demonstrated in the classification of some real credit scoring data. The comparison of correct classification rates of competing techniques shows the superiority of the generalized additive model using factor scores.