• Journal of the Korean Data and Information Science Society
• /
• v.28 no.5
• /
• pp.1087-1097
• /
• 2017

This study aims to find the best model to fit the number of insurance solicitor's turnovers of life insurance companies using count data regression models such as poisson regression, negative binomial regression, zero-inflated poisson regression, or zero-inflated negative binomial regression. Out of the four models, zero-inflated negative binomial model has been selected based on AIC and SBC criteria, which is due to over-dispersion and high proportion of zero-counts. The significant factors to affect insurance solicitor's turnover found to be a work period in current company, a total work period as financial planner, an affiliated corporation, and channel management satisfaction. We also have found that as the job satisfaction or the channel management satisfaction gets lower as channel management satisfaction, the number of insurance solicitor's turnovers increases. In addition, the total work period as financial planner has positive relationship with the number of insurance solicitor's turnovers, but the work period in current company has negative relationship with it.

• 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.

• Journal of Korean Academy of Nursing
• /
• v.44 no.6
• /
• pp.743-750
• /
• 2014

Purpose: The objective of this study was to provide a trend analysis of the prevalence of diabetes relative to the socioeconomic, lifestyle, and physiologic risk factors among Korean adults aged over 30 years for a 10-year period using data from the Korean National Health and Nutrition Examination Survey. Methods: Prevalence difference and the slope index of inequality were calculated for each risk factors using binomial regression by considering the repeated cross-sectional features of the data. The prevalence ratio and the relative index of inequality were calculated using log-binomial regression. Linear trend tests were performed using SAS 9.2. Results: Crude prevalence of diabetes increased over the 10-year period, and was higher for men than for women. It was very high for adults 60 years or over, consistently increasing over time. The prevalence among unemployed men, women with higher level of stress, women with hypertension, and adults with serum triglyceride levels over 135 mg/dL increased over the 10-year period in comparison with the respective control group. Conclusion: Considering the rapid economic development and associated lifestyle changes in Korea, action should be taken to control the prevalence of diabetes by both preventing and consistently monitoring these identified risk factors using a public-health approach.

• The Korean Journal of Applied Statistics
• /
• v.17 no.1
• /
• pp.13-26
• /
• 2004

According to economic growth theory, location configuration of business enterprises engaged in specific industries has spatial affinity. In this research we defined industrial concentration index to measure industry agglomeration using the characteristics of dispersion parameter of negative binomial distribution, and used the industrial concentration index to examine aspect of spatial configuration change. We utilized Census on Basic Characteristics of Establishments of 1995 and 2000 to deduce industrral concentration indices of 7 knowledge-based industries and 9 strategy-based industries of Choongbuk Province and analyzed the aspect of spatial configuration change.

• The Korean Journal of Applied Statistics
• /
• v.21 no.4
• /
• pp.603-613
• /
• 2008

We often encounter the situation that discrete count data have a large portion of zeros. In this case, it is not appropriate to analyze the data based on standard regression models such as the poisson or negative binomial regression models. In this article, we consider Bayesian analysis for two commonly used models. They are zero-inflated poisson and negative binomial regression models. We use the Bayes factor as a model selection tool and computation is proceeded via Markov chain Monte Carlo methods. Crash count data are analyzed to support theoretical results.

• The Korean Journal of Applied Statistics
• /
• v.16 no.2
• /
• pp.335-349
• /
• 2003

In this paper, we use Bayesian method for model selection of poisson vs. negative binomial distribution, and normal, double exponential vs. cauchy distribution. The fractional Bayes factor of O'Hagan (1995) was applied to Bayesian model selection under the assumption of noninformative improper priors for all parameters in the models. Through the analyses of real data and simulation data, we examine the usefulness of the fractional Bayes factor in comparison with intrinsic Bayes factors of Berger and Pericchi (1996, 1998).

• Journal of Family Relations
• /
• v.20 no.4
• /
• pp.131-156
• /
• 2016

Objective: This study aimed to examine parenting education participation of Korean mothers in the transition to parenthood and its related variables. Method: A study sample was composed of 870 mothers whose first child was younger than one-year old from the Panel Study on Korean Children in 2008(mean age=30.1, SD = 3.69). The descriptive statistics of parenting education participation were presented. In addition, negative binomial and logistic regression models were used in Stata13 in order to examine the variables related to parenting education participation of mothers in the transition to parenthood. Results: Approximately 82% of the mothers reported that they had participated in at least one parenting education program. Further, mother's educational level, monthly household income, mother's working experience, and community type generally predicted parenting education participation of mothers. However, the effects of these variables varied by the subjects and the providing institutions. Conclusion: This study provides the overall picture of parenting education participation of Korean mothers in the transition to parenthood and its related variables. The findings can be utilized to plan more effective parenting education programs for new parents.

• Communications for Statistical Applications and Methods
• /
• v.19 no.4
• /
• pp.537-546
• /
• 2012

In this paper, for analyzing binary data, Poisson regression with offset and logistic regression are compared with respect to the power via simulations. Poisson distribution can be used as an approximation of binomial distribution when n is large and p is small; however, we investigate if the same conditions can be held for the power of significant tests between logistic regression and offset poisson regression. The result is that when offset size is large for rare events offset poisson regression has a similar power to logistic regression, but it has an acceptable power even with a moderate prevalence rate. However, with a small offset size (< 10), offset poisson regression should be used with caution for rare events or common events. These results would be good guidelines for users who want to use offset poisson regression models for binary data.

• Proceedings of the Korean Statistical Society Conference
• /
• 2000.11a
• /
• pp.33-38
• /
• 2000

Krishnamoorphy and Raghavarao(1993) invented exact binomial and asymptotically normal test procedures for truthful answering in the repeated randomized response models under the assumption that two repeated response measures are independent. Under the same assumption, Lakshmi and Raghavarao(1992) suggested asymptotic chi-square test for respondents' truthful answering in the same models. In this article we detect the factors and the conditions with which two response variables might be independent, and find the condition for independence in the repeated randomized response models with considering untruthful answer. But, the condition of independence make the randomized model no meaning. Under the assumption of conditional independence between two response variables, we can apply the same logical statements on deriving the tests for truthful answering in the repeated randomized response models as in Krishnamoorphy and Raghavarao(1993).

• Communications for Statistical Applications and Methods
• /
• v.21 no.3
• /
• pp.261-274
• /
• 2014

In this paper we develop Bayes and empirical Bayes estimators of the finite population mean with the assumption of posterior linearity rather than normality of the superpopulation under the balanced loss function. We compare the performance of the optimal Bayes estimator with ones of the classical sample mean and the usual Bayes estimator under the squared error loss with respect to the posterior expected losses, risks and Bayes risks when the underlying distribution is normal as well as when they are binomial and Poisson.