• 응용통계연구
• /
• 제22권4호
• /
• pp.819-827
• /
• 2009

김인영 등 (2006)은 두 개 포아송 분포의 혼합모형에 기초한 회귀모형으로써 2002년 (사)볼런티어 21에서 실시한 설문조사 자료를 분석하여 우리나라 개인들이 기부한 횟수에 영향을 미치는 유의적 변수들을 식별하였다. 본고에서는 김인영 등 (2006)에서도 언급하였듯이 기부횟수 0의 관찰 빈도와 예측 빈도간 차이가 유독 큰 점을 감안하여, 0이 팽창된 포아송(zero inflated Poisson: ZIP)을 기존의 두 개의 포아송 혼합분포에 추가하여 일종의 세 개 포아송 혼합분포 형태로 모집단 분포를 구성하며 동 모형의 회귀모형으로써 기부횟수 자료를 재분석하고자 한다. 회귀계수에 대한 추정은 두 단계 EM 알고리즘으로 이루어 졌고, 유의적 설명 변수의 검색은 김인영 등 (2006)과 같았으나 본 연구에서는 고정된 령(零)군의 비율을 0.201로 추정할 수 있었으며, 두 가지 유의적 설명변수인 소득과 자원봉사 중에서 자원봉사가 기부 횟수를 늘리는 안정적 도구 변수로써 작용할 수 있음을 보고하고 있다.

• 응용통계연구
• /
• 제19권1호
• /
• pp.1-12
• /
• 2006

본 논문에서는 2002년에 (사)볼런티어21에서 실시한 설문조사 자료를 이용하여 2001년에 우리나라 개인들이 기부한 횟수에 영향을 주는 유의한 변수들을 식별하였다. 기부횟수의 경험적 분포로 미루어 모집단은 기부를 적게 하는 집단과 많이 하는 집단으로 구성되며 따라서 모집단 분포를 두개 포아송 분포의 혼합분포로 모형화하였다. 이 모형에 기초하여 기부횟수에 영향을 미치는 변수들을 식별하였다. EM알고리즘을 이용하여 모수를 추정하고 2.5%와 97.5%에 기초한 백분위수 신뢰구간을 보완한 BCa(bias-corrected and accelerated) 신뢰구간을 계산하여 유의한 변수들을 찾았다. 연구결과 혼합 포아송 회귀모형에서는 기부횟수가 적은 집단("작은 군")과 기부횟수가 많은 집단("큰 군") 모두에서 소득과 자원봉사의 경험 유무(1:예, 0:아니오)가 기부횟수에 유의적으로 영향을 주는 변수로 밝혀졌다. 또한 두 변수 각각에서 회귀계수가 양수로 나타나 소득이 많을수록, 혹은 자원봉사의 경험이 있는 사람일수록 기부횟수가 증가하는 것을 알 수 있다. 그러나 소득과 자원봉사 변수의 회귀계수는 "작은 군"이 "큰 군"에 비해 더욱 크게 나타나고 있다. "작은 군"보다 "큰 군"의 사람들에게 기부가 생활화되어 있고, 따라서 소득과 자원봉사의 경험 유무가 기부횟수에 미치는 영향이 상대적으로 적은 것으로 파악된다.

• 응용통계연구
• /
• 제27권5호
• /
• pp.743-753
• /
• 2014

Kim 등 (2006)과 Kim 등 (2009)은 2002년에 (사)볼런티어 21에서 조사한 설문자료에 기초하여 우리나라 개인의 기부횟수에 영향을 주는 유의적 설명변수를 보고한 바 있다. 본고에서는 Kim 등 (2006)과 Kim 등 (2009)의 계산오류를 발견하여 이를 수정하고, 아울러 Kim 등 (2009)이 적용한 0이 팽창된 포아송 모형에 로지스틱 회귀모형을 추가하였다. 동 로지스틱 모형으로 기부행위(0, 1)에 영향을 주는 설명변수를 식별하고, 아울러 기부횟수가 작은 군(群)과 큰 군(群)을 판별하여 주는 설명변수를 식별하고자 한다.

• 응용통계연구
• /
• 제21권5호
• /
• pp.835-843
• /
• 2008

In this paper, we investigate a Bayesian inference for software reliability models based on mean value functions which take the form of the mixture of beta distribution functions. The posterior simulation via the Markov chain Monte Carlo approach is used to produce estimates of posterior properties. Its applicability is illustrated with two real data sets. We compute the predictive distribution and the marginal likelihood of various models to compare the performance of them. The model comparison results show that the model based on the beta-mixture performs better than other models.

• Communications for Statistical Applications and Methods
• /
• 제25권2호
• /
• pp.173-184
• /
• 2018

In medical or public health research, it is common to encounter clustered or longitudinal count data that exhibit excess zeros. For example, health care utilization data often have a multi-modal distribution with excess zeroes as well as a multilevel structure where patients are nested within physicians and hospitals. To analyze this type of data, zero-inflated count models with mixed effects have been developed where a count response variable is assumed to be distributed as a mixture of a Poisson or negative binomial and a distribution with a point mass of zeros that include random effects. However, no study has considered a situation where data are also censored due to the finite nature of the observation period or follow-up. In this paper, we present a weighted version of zero-inflated Poisson model with random effects accounting for variable individual follow-up times. We suggested two different types of weight function. The performance of the proposed model is evaluated and compared to a standard zero-inflated mixed model through simulation studies. This approach is then applied to Medicaid data analysis.

• Ocean Systems Engineering
• /
• 제12권1호
• /
• pp.63-86
• /
• 2022

A refined projection-based purely Lagrangian meshfree method is presented towards reliable numerical analysis of fluid flow interactions with saturated/unsaturated porous media of uniform/spatially-varying porosities. The governing equations are reformulated on the basis of two-phase mixture theory with incorporation of volume fraction. These principal equations of mixture are discretized in the context of Incompressible SPH (Smoothed Particle Hydrodynamics) method. Associated with the consideration of governing equations of mixture, a new term arises in the source term of PPE (Poisson Pressure Equation), resulting in modified source term. The linear and nonlinear force terms are included in momentum equation to represent the resistance from porous media. Volume increase of fluid particles are taken into consideration on account of the presence of porous media, and hence multi-resolution ISPH framework is also incorporated. The stability and accuracy of the proposed method are thoroughly examined by reproducing several numerical examples including the interactions between fluid flow and saturated/unsaturated porous media of uniform/spatially-varying porosities. The method shows continuous pressure field, smooth variations of particle volumes and regular distributions of particles at the interface between fluid and porous media.

• International Journal of Concrete Structures and Materials
• /
• 제10권2호
• /
• pp.221-236
• /
• 2016

The aim of this paper is to investigate the compressive behavior and characteristics of amorphous metallic fiber-reinforced concrete (AMFRC). Compressive tests were carried out for two primary parameters: fiber volume fractions ($V_f$) of 0, 0.3, 0.6 and 0.8 %; and design compressive strengths of 27, 35, and 50 MPa at the age of 28 days. Test results indicated that the addition of amorphous metallic fibers in concrete mixture enhances the toughness, strain corresponding to peak stress, and Poisson's ratio at high stress level, while the compressive strength at the 28-th day is less affected and the modulus of elasticity is reduced. Based on the experimental results, prediction equations were proposed for the modulus of elasticity and strain at peak stress as functions of fiber volume fraction and concrete compressive strength. In addition, an analytical model representing the entire stress-strain relationship of AMFRC in compression was proposed and validated with test results for each concrete mix. The comparison showed that the proposed modeling approach can properly simulate the entire stress-strain relationship of AMFRC as well as the primary mechanical properties in compression including the modulus of elasticity and strain at peak stress.

• 응용통계연구
• /
• 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.

• Steel and Composite Structures
• /
• 제43권1호
• /
• pp.91-106
• /
• 2022

This paper has focused on presenting a three dimensional theory of elasticity for free vibration of 3D-graphene foam reinforced polymer matrix composites (GrF-PMC) cylindrical panels resting on two-parameter elastic foundations. The elastic foundation is considered as a Pasternak model with adding a Shear layer to the Winkler model. The porous graphene foams possessing 3D scaffold structures have been introduced into polymers for enhancing the overall stiffness of the composite structure. Also, 3D graphene foams can distribute uniformly or non-uniformly in the shell thickness direction. The effective Young's modulus, mass density and Poisson's ratio are predicted by the rule of mixture. Three complicated equations of motion for the panel under consideration are semi-analytically solved by using 2-D differential quadrature method. The fast rate of convergence and accuracy of the method are investigated through the different solved examples. Because of using two-dimensional generalized differential quadrature method, the present approach makes possible vibration analysis of cylindrical panels with two opposite axial edges simply supported and arbitrary boundary at the curved edges. It is explicated that 3D-GrF skeleton type and weight fraction can significantly affect the vibrational characteristics of GrF-PMC panel resting on two-parameter elastic foundations.

• Geomechanics and Engineering
• /
• 제24권3호
• /
• pp.267-280
• /
• 2021

The research presented in this paper deals with dynamic stability analysis of the graphene nanoplatelets (GPLs) reinforced composite spinning disk. The presented small-scaled structure is simulated as a disk covered by viscoelastic substrate which is two-parametric. The centrifugal and Coriolis impacts due to the spinning are taken into account. The stresses and strains would be obtained using the first-order-shear-deformable-theory (FSDT). For Poisson ratio, as well as various amounts of mass densities, the mixture rule is employed, while a modified Halpin-Tsai model is inserted for achieving the elasticity module. The structure's boundary conditions (BCs) are obtained employing GPLs reinforced composite (GPLRC) spinning disk's governing equations applying principle of Hamilton which is based on minimum energy and ultimately have been solved employing numerical approach called generalized-differential quadrature-method (GDQM). Spinning disk's dynamic properties with different boundary conditions (BCs) are explained due to the curves drawn by Matlab software. Also, the simply-supported boundary conditions is applied to edges 𝜃=𝜋/2, and 𝜃=3𝜋/2, while, cantilever, respectively, is analyzed in R=R_i, and R₀. The final results reveal that the GPLs' weight fraction, viscoelastic substrate, various GPLs' pattern, and rotational velocity have a dramatic influence on the amplitude, and vibration behavior of a GPLRC rotating cantilevered disk. As an applicable result in related industries, the spinning velocity impact on the frequency is more effective in the higher radius ratio's amounts.