• Journal of the Korean Statistical Society
• /
• v.31 no.1
• /
• pp.93-107
• /
• 2002

Random effects generalised linear models are useful for analysing clustered count data in which responses are usually correlated. We propose a Bayesian approach to parameter estimation and variable selection in random effects generalised linear models for count data. A simple Gibbs sampling algorithm for parameter estimation is presented and a simple and efficient variable selection is done by using the Gibbs outputs. An illustrative example is provided.

• Journal of the Korean Statistical Society
• /
• v.24 no.2
• /
• pp.349-360
• /
• 1995

This paper deals with the robustness properties of the minimum disparity estimation in linear regression models. The estimators defined as statistical quantities whcih minimize the blended weight Hellinger distance between a weighted kernel density estimator of the residuals and a smoothed model density of the residuals. It is shown that if the weights of the density estimator are appropriately chosen, the estimates of the regression parameters are robust.

• Communications for Statistical Applications and Methods
• /
• v.11 no.3
• /
• pp.519-527
• /
• 2004

Relationship between the partial likelihood ratio statistics for logisitic models and the partial goodness-of-fit statistics for corresponding log-linear models is discussed. This paper shows how definitions of suppression in logistic model can be adapted for log-linear model and how they are related to confounding in terms of collapsibility for categorical data. Several $2{times}2{times}2$ contingency tables are illustrated.

• Journal of Korea Water Resources Association
• /
• v.30 no.3
• /
• pp.279-291
• /
• 1997

This study is to evaluate the accuracy and practicality of the existing four conceptual models, two linear models of Clark and Nash model and two nonlinear models of Laruenson and WBN model, and to select an appropriate model to simulate the rainfall-runoff process in a given catchment. The variability of parameters for linear models is generally larger than that of nonlinear models. The errors in peak discharge are similar among the four conceptual models buy the errors in time to peak are quite different. Nonlinear models produce better results for time distribution than linear models. A comparison of the conceptual models to predict overall hydrograph using Friedman two-way analysis of variance by rank test indicates that nonlinear models are slightly better than linear models.

• Communications for Statistical Applications and Methods
• /
• v.13 no.3
• /
• pp.755-764
• /
• 2006

Most graphical methods for categorical data can describe the structure of data and represent a measure of association among categorical variables. Among them the polyhedron plot represents sequential relationships among hierarchical log-linear models for a multidimensional contingency table. This kind of plot could be explored to describe the differences among sequential models. In this paper we suggest graphical methods, containing all the information, that reflect the relationship among all log-linear models in a certain hierarchical structure. We use the ideas of a correlation diagram.

• The Korean Journal of Applied Statistics
• /
• v.6 no.2
• /
• pp.253-263
• /
• 1993

Recent interest in Taguchi's methods have led to developments of joint modelling of the mean and dispersion in generalized linear models. Since a single data transformation cannot produce all the necessary conditions for an analysis, for the analysis of the Taguchi data, the use of the generalized linear models is preferred to a commonly used data transformation method. In this paper, we will illustrate this point and provide GLIM macros to implement the joint modelling of the mean and dispersion in generalized linear models.

• Proceedings of the Safety Management and Science Conference
• /
• 2009.04a
• /
• pp.185-192
• /
• 2009

The research contributes extending and reviewing of restricted (constrained) and unrestricted (unconstrained) models in GLM(Generalized Linear Models). The paper includes the methodology for finding EMS(Expected Mean Square) and $F_0$ ratio. The results can be applied to the gauge R&R(Reproducibility and Repeatability) in MSA(Measurement System Analysis).

• Journal of the Korean Statistical Society
• /
• v.19 no.2
• /
• pp.171-175
• /
• 1990

A diagnostic test for detecting nonconstant variance in mixed linear models based on the score statistic is derived through the technique of model expansion, and compared to the log likelihood ratio test.

• Journal of Climate Change Research
• /
• v.34 no.20
• /
• pp.8257-8271
• /
• 2021

This study presents the ability of seasonal forecast models to represent the observed midlatitude teleconnection associated with El Niño-Southern Oscillation (ENSO) events over the North American region for the winter months of December, January, and February. Further, the impacts of the associated errors on regional forecast performance for winter temperatures are evaluated, with a focus on 1-month-lead-time forecasts. In most models, there exists a strong linear relationship of temperature anomalies with ENSO, and, thus, a clear anomaly sign separation between both ENSO phases persists throughout the winter, whereas linear relationships are weak in observations. This leads to a difference in the temperature forecast performance between the two ENSO phases. Forecast verification scores show that the winter-season warming events during El Niño in northern North America are more correctly forecast in the models than the cooling events during La Niña and that the winter-season cooling events during El Niño in southern North America are also more correctly forecast in the models than warming events during La Niña. One possible reason for this result is that the remote atmospheric teleconnection pattern in the models is almost linear or symmetric between the El Niño and La Niña phases. The strong linear atmospheric teleconnection appears to be associated with the models' failure in simulating the westward shift of the tropical Pacific Ocean rainfall response for the La Niña phase as compared with that for the El Niño phase, which is attributed to the warmer central tropical Pacific in the models. This study highlights that understanding how the predictive performance of climate models varies according to El Niño or La Niña phases is very important when utilizing predictive information from seasonal forecast models.

• Communications for Statistical Applications and Methods
• /
• v.30 no.5
• /
• pp.437-451
• /
• 2023

Generalized linear models and generalized linear mixed models (GLMMs) are fundamental tools for predictive analyses. In insurance, GLMMs are particularly important, because they provide not only a tool for prediction but also a theoretical justification for setting premiums. Although thousands of resources are available for introducing GLMMs as a classical and fundamental tool in statistical analysis, few resources seem to be available for the insurance industry. This study targets insurance professionals already familiar with basic actuarial mathematics and explains GLMMs and their linkage with classical actuarial pricing tools, such as the Buhlmann premium method. Focus of the study is mainly on the modeling aspect of GLMMs and their application to pricing, while avoiding technical issues related to statistical estimation, which can be automatically handled by most statistical software.