• Asian-Australasian Journal of Animal Sciences
• /
• 제13권3호
• /
• pp.413-422
• /
• 2000

In the class of models which include random effects, the variance component estimates are important to obtain accurate predictors and estimators. Variance component estimation is straightforward for balanced data but not for unbalanced data. Since orthogonality among factors is absent in unbalanced data, various methods for variance component estimation are available. REML estimation is the most widely used method in animal breeding because of its attractive statistical properties. Recently, Bayesian approach became feasible through Markov Chain Monte Carlo methods with increasingly powerful computers. Furthermore, advances in variance component estimation with complicated models such as generalized linear mixed models enabled animal breeders to analyze non-normal data.

• Communications for Statistical Applications and Methods
• /
• 제16권6호
• /
• pp.971-978
• /
• 2009

Poisson generalized linear mixed models(GLMMs) have been widely used for the analysis of clustered or correlated count data. For the inference marginal likelihood, which is obtained by integrating out random effects is often used. It gives maximum likelihood(ML) estimator, but the integration is usually intractable. In this paper, we propose how to obtain the ML estimator via Laplace approximation based on hierarchical-likelihood (h-likelihood) approach under the Poisson GLMMs. In particular, the h-likelihood avoids the integration itself and gives a statistically efficient procedure for various random-effect models including GLMMs. The proposed method is illustrated using two practical examples and simulation studies.

• Journal of the Korean Data and Information Science Society
• /
• 제10권2호
• /
• pp.329-340
• /
• 1999

We consider a Bayesian forcasting method for the analysis of repeated surveys. It is assumed that the parameters of the superpopulation model at each time follow a stochastic model. We propose Bayesian prediction procedures for the finite population total under multiprocess dynamic generalized linear models. The multiprocess dynamic model offers a powerful framework for the modelling and analysis of time series which are subject to a abrupt changes in pattern. Some numerical studies are provided to illustrate the behavior of the proposed predictors.

• Journal of the Korean Data and Information Science Society
• /
• 제19권4호
• /
• pp.1429-1440
• /
• 2008

In a meta-analysis combining the results from different clinical trials, it is important to consider the possible heterogeneity in outcomes between trials. Such variations can be regarded as random effects. Thus, random-effect models such as HGLMs (hierarchical generalized linear models) are very useful. In this paper, we propose a HGLM framework for analyzing the binominal response data which may have variations in the odds-ratios between clinical trials. We also present the prediction intervals for random effects which are in practice useful to investigate the heterogeneity of the trial effects. The proposed method is illustrated with a real-data set on 22 trials about respiratory tract infections. We further demonstrate that an appropriate HGLM can be confirmed via model-selection criteria.

• Journal of Environmental Science International
• /
• 제27권7호
• /
• pp.509-518
• /
• 2018

Weather is the most influential factor for crop cultivation. Weather information for cultivated areas is necessary for growth and production forecasting of agricultural crops. However, there are limitations in the meteorological observations in cultivated areas because weather equipment is not installed. This study tested methods of predicting the daily mean temperature in onion fields using geostatistical models. Three models were considered: inverse distance weight method, generalized additive model, and Bayesian spatial linear model. Data were collected from the AWS (automatic weather system), ASOS (automated synoptic observing system), and an agricultural weather station between 2013 and 2016. To evaluate the prediction performance, data from AWS and ASOS were used as the modeling data, and data from the agricultural weather station were used as the validation data. It was found that the Bayesian spatial linear regression performed better than other models. Consequently, high-resolution maps of the daily mean temperature of Jeonnam were generated using all observed weather information.

• Journal of the Korean Data and Information Science Society
• /
• 제27권5호
• /
• pp.1215-1224
• /
• 2016

Climate information of the high resolution grid units is an important factor to explain the phenomenon in a variety of research field. Statistical linear interpolation models are computationally inexpensive and applicable to any climate data compared to the dynamic simulation method at regional scales. In this paper, we considered four different linear-based statistical interpolation models: general linear model, generalized additive model, spatial linear regression model, and Bayesian spatial linear regression model. The climate variable of interest was the daily mean temperature, where the spatial variability was explained using geographic terrain information: latitude, longitude, elevation. The data were collected by weather stations in January from 2003 and 2012. In the sense of RMSE and correlation coefficient, Bayesian spatial linear regression model showed better performance in reflecting the spatial pattern compared to the other models.

• The Korean Journal of Applied Statistics
• /
• 제24권4호
• /
• pp.587-595
• /
• 2011

Credit scoring is an objective and automatic system to assess the credit risk of each customer. The logistic regression model is one of the popular methods of credit scoring to predict the default probability; however, it may not detect possible nonlinear features of predictors despite the advantages of interpretability and low computation cost. In this paper, we propose to use a generalized partially linear model as an alternative to logistic regression. We also introduce modern ensemble technologies such as bagging, boosting and random forests. We compare these methods via a simulation study and illustrate them through a German credit dataset.

• The Korean Journal of Applied Statistics
• /
• 제25권6호
• /
• pp.1037-1047
• /
• 2012

The generalized linear mixed model(GLMM) is widely used in fitting categorical responses of clustered data. In the numerical approximation of likelihood function the normality is assumed for the random effects distribution; subsequently, the commercial statistical packages also routinely fit GLMM under this normality assumption. We may also encounter departures from the distributional assumption on the response variable. It would be interesting to investigate the impact on the estimates of parameters under misspecification of distributions; however, there has been limited researche on these topics. We study the sensitivity or robustness of the maximum likelihood estimators(MLEs) of GLMM for counts data when the true underlying distribution is normal, gamma, exponential, and a mixture of two normal distributions. We also consider the effects on the MLEs when we fit Poisson-normal GLMM whereas the outcomes are generated from the negative binomial distribution with overdispersion. Through a small scale Monte Carlo study we check the empirical coverage probabilities of parameters and biases of MLEs of GLMM.

• The Korean Journal of Applied Statistics
• /
• 제17권2호
• /
• pp.337-346
• /
• 2004

The Pearson chi-square goodness-of-fit test and the likelihood ratio tests are usually used for testing independence in two-way contingency tables under random sampling. But both of these tests may provide false results for the contingency table with clustered observations. In this case we consider the generalized linear mixed model which includes random effects of clustering in addition to the fixed effects of covariates. Both the heterogeneity between clusters and the dependency within a cluster can be explained via generalized linear mixed model. In this paper we introduce several types of generalized linear mixed model for testing independence in contingency tables with clustered observations. We also discuss the fitting of these models through a real dataset.

• Communications for Statistical Applications and Methods
• /
• 제25권1호
• /
• pp.61-70
• /
• 2018

Modeling of the random effects covariance matrix in generalized linear mixed models (GLMMs) is an issue in analysis of longitudinal categorical data because the covariance matrix can be high-dimensional and its estimate must satisfy positive-definiteness. To satisfy these constraints, we consider the autoregressive and moving average Cholesky decomposition (ARMACD) to model the covariance matrix. The ARMACD creates a more flexible decomposition of the covariance matrix that provides generalized autoregressive parameters, generalized moving average parameters, and innovation variances. In this paper, we analyze longitudinal count data with overdispersion using GLMMs. We propose negative binomial loglinear mixed models to analyze longitudinal count data and we also present modeling of the random effects covariance matrix using the ARMACD. Epilepsy data are analyzed using our proposed model.