• Journal of the Korean Statistical Society
• /
• 제31권1호
• /
• pp.93-107
• /
• 2002

Random effects generalised linear models are useful for analysing clustered count data in which responses are usually correlated. We propose a Bayesian approach to parameter estimation and variable selection in random effects generalised linear models for count data. A simple Gibbs sampling algorithm for parameter estimation is presented and a simple and efficient variable selection is done by using the Gibbs outputs. An illustrative example is provided.

• Journal of the Korean Statistical Society
• /
• 제36권4호
• /
• pp.523-542
• /
• 2007

In this paper we consider semiparametric random effect panel models that contain AR(p) disturbances. We derive the efficient score function and the information bound for estimating the slope parameters. We make minimal assumptions on the distribution of the random errors, effects, and the regressors, and provide semiparametric efficient estimates of the slope parameters. The present paper extends the previous work of Park et al.(2003) where AR(1) errors were considered.

• Journal of the Korean Data and Information Science Society
• /
• 제20권1호
• /
• pp.203-209
• /
• 2009

Frailty models are useful for the analysis of correlated and/or heterogeneous survival data. However, the inferences of fixed parameters, rather than random effects, have been mainly studied. The prediction (or estimation) of random effects is also practically useful to investigate the heterogeneity of the hospital or patient effects. In this paper we propose how to extend the prediction method for random effects in HGLMs (hierarchical generalized linear models) to log-normal semiparametric frailty models with nonparametric baseline hazard. The proposed method is demonstrated by a simulation study.

• Journal of the Korean Statistical Society
• /
• 제30권4호
• /
• pp.541-550
• /
• 2001

This paper considers a panel data regression model in which the disturbances follow a nested error components with serial correlation. Given this model, this paper derives several Lagrange Multiplier(LM) testis for the presence of serial correlation as well as random individual effects, nested effects, and for existence of serial correlation given random individual and nested effects.

• Journal of the Korean Data and Information Science Society
• /
• 제12권1호
• /
• pp.19-25
• /
• 2001

Random effects models which describe the dependence via random effects in various correlated data have recently received considerable attention in the biomedical literature. They include mixed linear models (MLMs), generatized linear mixed models (GLMMS) and hierarchical generalized linear models (HGLMs). For the inference Lee and Nelder (2000) proposed the first-and second-order REML (restricted maximum likelihood) methods based on hierarchical-likelihood of tee and Welder (1996). In this paper, for Poisson-gamma HGLMs the new methods are theoretically compared with marginal likelihood methods and both methods are illustrated by two practical examples.

• 아동학회지
• /
• 제22권4호
• /
• pp.167-188
• /
• 2001

This study investigated the relationship of daily life activity experiences to violent behaviors and their moderating effects on the relationship between stress and violent behaviors in early adolescence. A sample of 134 second year middle school students carried electronic watches for one week and provided reports on their objective activity situation and subjective states when signalled at random times. Stress was positively correlated with violent behaviors. Daily activity experiences were correlated with violent behaviors and moderated the relationship between stress and violent behaviors. More time spent in socializing and passive leisure, and negative emotional states during schoolwork and active leisure were correlated with higher violent behaviors. Lower motivational states during schoolwork were correlated with higher violent behaviors. Lower cognition of importance and attention states during schoolwork and higher cognition of importance and attention states during active leisure and maintenance activities were correlated with higher violent behaviors. Finally, the moderating effects of negative emotion during active leisure, motivation and attention states during schoolwork on the relationship of stress with violent behaviors were found among girls only.

• 노동경제논집
• /
• 제43권4호
• /
• pp.179-203
• /
• 2020

본 연구는 사업체패널조사와 노동패널조사를 사용하여 노동조합이 교육훈련에 미치는 영향을 비교·분석하였다. 상관임의효과(Correlated Random Effect: CRE) 모형을 적용한 사업체 및 개인 단위의 분석 결과를 살펴보면, 두 결과 모두에서 노동조합은 교육훈련을 증가시키는 것으로 나타났다. 노동조합의 존재는 사업체의 교육훈련 실시를 약 4.7%p, 개별 근로자들의 교육훈련 참여를 약 1.7%p 높이는 것으로 추정되었으며, 이상의 분석 결과는 근로자를 위한 교육훈련을 늘리기 위한 노동조합의 역할을 시사하고 있다.

• 응용통계연구
• /
• 제30권6호
• /
• pp.957-981
• /
• 2017

관측되지 않는 효과 또는 고정효과로 설명할 수 없는 분산 구조가 포함되어 정확한 모수 추정이 어려운 경우 체계적인 분석을 위해 일반화 선형 모형은 임의효과가 포함된 일반화 선형 혼합 모형으로 확장되었다. 본 연구에서는 일반화 선형 모형 중에서도 이분적인 반응변수를 다루는 로지스틱 회귀모형에 임의효과를 포함한 최대 우도 추정 방법을 설명한다. 그중에서도 라플라스 근사법, 가우스-에르미트 구적법, 적응 가우스-에르미트 구적법 그리고 유사가능도 우도에 대한 최대우도 추정법을 자세히 알아본다. 또한 제안한 방법을 사용하여 한국 복지 패널 데이터에서 정신건강과 생활만족도가 자원봉사활동에 미치는 영향에 대해 분석한다.

• 응용통계연구
• /
• 제31권2호
• /
• pp.287-301
• /
• 2018

0이 과도하게 많이 나타나는 자료는 여러 다양한 분야에서 흔히 볼 수 있다. 이러한 자료들을 분석할 때 대표적으로 영과잉 포아송 모형이 사용된다. 특히 반응변수들 사이에 상관관계가 존재할 때에는 랜덤효과를 영과잉 포아송 모형에 도입해서 분석해야 한다. 이러한 모형은 주로 빈도론자들의 접근방법으로 분석되어왔는데, 최근에는 베이지안 기법을 사용한 분석도 다양하게 발전되어 왔다. 본 논문에서는 반응변수들 사이에 상관관계가 존재하는 경우 랜덤효과가 포함된 영과잉 포아송 회귀모형을 베이지안 추론 방법을 토대로 제안하였다. 이 모형의 적합성을 판단하기 위해 모의 실험을 통해 랜덤효과를 고려하지 않은 모형과 비교 분석하였다. 또한, 실제 지역사회 건강조사 흡연 자료에 직접 응용하여 그 결과를 살펴보았다.

• Communications for Statistical Applications and Methods
• /
• 제15권6호
• /
• pp.969-976
• /
• 2008

Mixed linear models have been widely used in various correlated data including multivariate survival data. In this paper we extend hierarchical-likelihood(h-likelihood) approach for mixed linear models with right censored data to that for left censored data. We also allow a general random-effect structure and propose the estimation procedure. The proposed method is illustrated using a numerical data set and is also compared with marginal likelihood method.