• Communications for Statistical Applications and Methods
• /
• 제19권4호
• /
• 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.

• Journal of the Korean Data and Information Science Society
• /
• 제14권1호
• /
• pp.45-53
• /
• 2003

The Zero-Inflated Poisson regression is a model for count data with exess zeros. When the reponse variables have excess zeros, it is not easy to apply the Poisson regression model. In this paper, we study and simulate the zero-inflated Poisson regression model. An real example was applied to this model. Regression parameters are estimated by using MLE's. We also compare the fitness of zero-inflated Poisson model with the Poisson regression and decision tree model.

• Journal of the Korean Data and Information Science Society
• /
• 제23권6호
• /
• pp.1231-1239
• /
• 2012

An estimating procedure is introduced for kernel Poisson regression when the input variables consist of numerical and categorical variables, which is based on the penalized negative log-likelihood and the component-wise product of two different types of kernel functions. The proposed procedure provides the estimates of the mean function of the response variables, where the canonical parameter is linearly and/or nonlinearly related to the input variables. Experimental results are then presented which indicate the performance of the proposed kernel Poisson regression.

• 품질경영학회지
• /
• 제33권1호
• /
• pp.83-87
• /
• 2005

For the count response we normally consider Poisson regression model. However, the conventional fitting algorithm for Poisson regression model is not reliable at all when the response variable is measured with sizable contamination. In this study, we propose an alternative fitting algorithm that is resistant to outlying values in response and report a case study in semiconductor industry.

• Journal of the Korean Data and Information Science Society
• /
• 제14권2호
• /
• pp.177-186
• /
• 2003

The Zero-Inflated Poisson regression is a model for count data with exess zeros. When the correlated response variables are intrested, we have to extend the univariate zero-inflated regression model to multivariate model. In this paper, we study and simulate the multivariate zero-inflated regression model. A real example was applied to this model. Regression parameters are estimated by using MLE's. We also compare the fitness of multivariate zero-inflated Poisson regression model with the decision tree model.

• 응용통계연구
• /
• 제19권3호
• /
• pp.505-519
• /
• 2006

셀 수 있는 이산 자료(discrete count data)에 대한 분석은 여러 분야에서 활용되고 있지만 영(zero)을 과도하게 포함하고 있는 영과잉 자료는 자료의 성격상 포아송 분포를 따르지 못할 때가 있어 분석에 어려움이 따른다. Zero-Inflated Poisson(ZIP)모형은 이런 어려움을 극복하기 위하여 영에 대한 점확률을 가지는 분포와 포아송 분포를 합성하여 과도한 영과 영이 아닌 자료를 설명하는 모형이다. 설명 변수가 존재할 때는 포아송 분포 부분에서 반응변수의 평균과 공변량사이에 로그선형 연결함수를 사용한 Zero-Inflated Poisson Regression(ZIPR)모형이 사용될 수 있다. 본 논문에서는 Markov Chain Monte Carlo 기법을 이용한 ZIPR모형의 베이지안 추론방법을 제안하고, 이를 실제 구강위생 자료에 적용하며 다른 모형들과 비교한다. 그 결과 베이지안 추론 방법을 적용한 영과잉 모형의 추정오차가 다른 모형들의 추정오차보다 작았고, 예측치가 더 정확했다는 점에서 우수함을 알 수 있었다.

• Journal of the Korean Data and Information Science Society
• /
• 제18권3호
• /
• pp.767-772
• /
• 2007

A kernel machine is proposed as an estimating procedure for the linear and nonlinear Poisson regression, which is based on the penalized negative log-likelihood. The proposed kernel machine provides the estimate of the mean function of the response variable, where the canonical parameter is related to the input vector in a nonlinear form. The generalized cross validation(GCV) function of MSE-type is introduced to determine hyperparameters which affect the performance of the machine. Experimental results are then presented which indicate the performance of the proposed machine.

• Communications for Statistical Applications and Methods
• /
• 제29권4호
• /
• pp.413-420
• /
• 2022

In this study we adapt discrete weibull regression model for clustered count data. Discrete weibull regression model has an attractive feature that it can handle both under and over dispersion data. We analyzed the eighth Korean National Health and Nutrition Examination Survey (KNHANES VIII) from 2019 to assess the factors influencing the 1 month outpatient stay in 17 different regions. We compared the results using clustered discrete Weibull regression model with those of Poisson, negative binomial, generalized Poisson and Conway-maxwell Poisson regression models, which are widely used in count data analyses. The results show that the clustered discrete Weibull regression model using random intercept model gives the best fit. Simulation study is also held to investigate the performance of the clustered discrete weibull model under various dispersion setting and zero inflated probabilities. In this paper it is shown that using a random effect with discrete Weibull regression can flexibly model count data with various dispersion without the risk of making wrong assumptions about the data dispersion.

• Communications for Statistical Applications and Methods
• /
• 제26권6호
• /
• pp.527-538
• /
• 2019

This paper considers the issue of obtaining the optimal design in Poisson regression model when the sample size is small. Poisson regression model is widely used for the analysis of count data. Asymptotic theory provides the basis for making inference on the parameters in this model. However, for small size experiments, asymptotic approximations, such as unbiasedness, may not be valid. Therefore, first, we employ the second order expansion of the bias of the maximum likelihood estimator (MLE) and derive the mean square error (MSE) of MLE to measure the quality of an estimator. We then define DM-optimality criterion, which is based on a function of the MSE. This criterion is applied to obtain locally optimal designs for small size experiments. The effect of sample size on the obtained designs are shown. We also obtain locally DM-optimal designs for some special cases of the model.

• 한국도로학회논문집
• /
• 제14권4호
• /
• pp.83-91
• /
• 2012

PURPOSES : This study deals with Rotary by Accident Occurrence Location. The purpose of this study is to develop the accident models of rotary by location. METHODS : In pursuing the above, this study gives particular attentions to developing the appropriate models using multiple linear, Poisson and negative binomial regression models and statistical analysis tools. RESULTS : First, four multiple linear regression models which are statistically significant(their $R^2$ values are 0.781, 0.300, 0.784 and 0.644 respectively) are developed, and four Poisson regression models which are statistically significant(their ${\rho}^2$ values are 0.407, 0.306, 0.378 and 0.366 respectively) are developed. Second, the test results of fitness using RMSE, %RMSE, MPB and MAD show that Poisson regression model in the case of circulatory roadway, pedestrian crossing and others and multiple linear regression model in the case of entry/exit sections are appropriate to the given data. Finally, the common variable that affects to the accident is adopted to be traffic volume. CONCLUSIONS : 8 models which are all statistically significant are developed, and the common and specific variables that are related to the models are derived.