• Communications for Statistical Applications and Methods
• /
• v.10 no.2
• /
• pp.585-594
• /
• 2003

It has been generally recognized that conventional binomial or Poisson model provides poor fits to the actual correlated binary data due to the extra-binomial variation. A number of generalized statistical models have been proposed to account for this additional variation. Among them, beta-binomial, correlated-binomial, and modified-binomial models are binomial-related models which are frequently used in modeling the sum of n correlated binary data. In many situations, it is reasonable to assume that n correlated binary data are exchangeable, which is a special case of correlated binary data. The sum of n exchangeable correlated binary data is modeled relatively well when the above three binomial-related models are applied. But the estimation results of correlation coefficient turn to be quite different. Hence, it is important to identify which model provides better estimates of model parameters(success probability, correlation coefficient). For this purpose, a small-scale simulation study is performed to compare the behavior of above three models.

• Journal of the Korean Data and Information Science Society
• /
• v.19 no.4
• /
• pp.1327-1334
• /
• 2008

Mixed effect binomial regression models are widely used for analysis of correlated count data in which the response is the result of a series of one of two possible disjoint outcomes. In this paper, we consider kernel extensions with nonparametric fixed effects and parametric random effects. The estimation is through the penalized likelihood method based on kernel trick, and our focus is on the efficient computation and the effective hyperparameter selection. For the selection of hyperparameters, cross-validation techniques are employed. Examples illustrating usage and features of the proposed method are provided.

• Communications for Statistical Applications and Methods
• /
• v.23 no.5
• /
• pp.433-444
• /
• 2016

When we observe binary responses in a cluster (such as rat lab-subjects), they are usually correlated to each other. In clustered binomial counts, the independence assumption is violated and we encounter an extra-variation. In the presence of extra-variation, the ordinary statistical analyses of binomial data are inappropriate to apply. In testing the homogeneity of proportions between several treatment groups, the classical Pearson chi-squared test has a severe flaw in the control of Type I error rates. We focus on modifying the chi-squared statistic by incorporating variance inflation factors. We suggest a method to adjust data in terms of dispersion estimate based on a quasi-likelihood model. We explain the testing procedure via an illustrative example as well as compare the performance of a modified chi-squared test with competitive statistics through a Monte Carlo study.

• The Korean Journal of Applied Statistics
• /
• v.28 no.2
• /
• pp.231-239
• /
• 2015

A Poisson model is the first choice for counts data. Quasi Poisson or negative binomial models are usually used in cases of over (or under) dispersed data. However, these models might be unsuitable if the data consist of excessive number of zeros (zero inflated data). For zero inflated counts data, Zero Inflated Poisson (ZIP) or Zero Inflated Negative Binomial (ZINB) models are recommended to address the issue. In this paper, we further considered a situation where zero inflated data are spatially correlated. A mixed effect model with random effects that account for spatial autocorrelation is used to fit the data.

• Communications for Statistical Applications and Methods
• /
• v.18 no.4
• /
• pp.507-516
• /
• 2011

Comparative studies on generalized binomial models (Moon, 2003; Ng, 1989; Paul, 1985; Kupper and Haseman, 1978; Griffiths, 1973) are restrictive in that the models compared are rather limited and MSE of the estimates is the only measure considered for the model adequacy. This paper is aimed to report simulation results which provide possible guidelines for selecting a proper model. We examine Pearson type of goodness-of-fit statistic to its degrees of freedom and AIC for the overall model quality. MSE and Bias of the individual estimates are also considered as the component fit measures. Performance of some models varies widely for a certain range of the parameter space while most of the models are quite competent. Our evaluation shows that the Extended Beta-Binomial model (Prentice, 1986) turns out to be particularly favorable in the point that it provides consistently excellent fit almost all over the values of the intra-class correlation coefficient and the probability of success.

• The Korean Journal of Applied Statistics
• /
• v.21 no.6
• /
• pp.923-932
• /
• 2008

We are likely to face complex multivariate data which can be characterized by having a non-trivial correlation structure. For instance, omitted covariates may simultaneously affect more than one count in clustered data; hence, the modeling of the correlation structure is important for the efficiency of the estimator and the computation of correct standard errors, i.e., valid inference. A standard way to insert dependence among counts is to assume that they share some common unobservable variables. For this assumption, we fitted correlated random effect models considering multilevel model. Estimation was carried out by adopting the semiparametric approach through a finite mixture EM algorithm without parametric assumptions upon the random coefficients distribution.

• Journal of Oriental Neuropsychiatry
• /
• v.34 no.4
• /
• pp.349-358
• /
• 2023

Objectives: We used the 2019 Korea Health Panel Annual Data to analyze factors related to visits to Korean medicine (KM) outpatient clinics among patients with mood disorders in Korea. Methods: Individuals aged 19 years or older, with depressive or bipolar disorders, and with a record of using Western medicine (WM) and/or the KM medical service were included. The 266 subjects were classified into the WM group or the integrative medicine (IM) group. The Andersen healthcare utilization model was used to analyze factors that potentially influenced the subjects' healthcare utilization. Binomial logistic regression analysis was used to analyze factors influencing the use of IM medical services. Results: Among the subjects, 75.56% (n=201) were in the WM group, and 24.44% (n=65) were in the IM group. Statistically significant differences were observed in residential areas, total annual income, the presence of disability, and the level of pain/discomfort between the two groups. Regression analysis found that residential areas and pain/discomfort were factors related to the use of IM services. Specifically, reporting "a lot" of pain/discomfort compared to "no" pain/discomfort showed a significant positive relationship with the use of IM (odds ratio=4.57, 95% confidence interval=1.79 to 11.70). Conclusions: This study was the first to analyze the status of KM medical service use and related factors among patients with mood disorders in Korea. The finding that the presence of pain/discomfort was positively correlated with the use of KM services is potentially related to medically unexplained physical symptoms or somatization phenomena.

• Journal of Technology Innovation
• /
• v.26 no.4
• /
• pp.29-56
• /
• 2018

The purpose of this research is to examine whether investment portfolio composition affects the technological performance of corporate venture capital (CVC). The stages of investment are categorized from "start-up/seed", "early", and "expansion", to "later" stage. We posit and test that the investment stage composition in a portfolio is highly correlated with the growth potential and downside risk of the portfolio, which in turn influences an investor's innovation performance. To test this hypothesis, we used negative binomial panel regression with 21 years of deal data from 70 cases of CVC. The results show that there is an inverted U shaped relationship between investment portfolio composition and technological performance. This means that the more seed or early stage investment within the investment portfolio, the higher the innovation performance; however, if the amount of seed or early stage investment is over a certain level, the performance decreases. Further, this study finds that the external partners of a venture negatively moderate the inverted U shaped relationship between portfolio composition and innovation performance. We believe that corporate planners, venture capitalists, and policy makers will be helped by these results showing that companies can maximize their investment performance by considering the investment stage and progress of investments.