• Communications for Statistical Applications and Methods
• /
• v.2 no.2
• /
• pp.155-165
• /
• 1995

반복측정자료의 분석을 위해 제안된 Liang and Zeger(1986)의 회귀모형은 일반화추정식(generalized estimationg equations, GEE)을 이용하여 모형의 모수를 추정한다. 이 모형은 반복측정된 반응변수와 설명변수들과의 관계를 추정하는 것이 주된 목적이기 때문에 회귀모수는 중요한 모수로 간주되나 산포모수는 중요하지 않은 장애모수(nuisance parameters)로 간주된다. 일반적으로 GEE 분석에서 회귀모수의 추정량은 산포모수에 상관없이 일치적(consistent)으로 얻어진다고 알려져 있다. 그러나 본 논문에서는 포아송분포를 따르는 반복측정자료에 대한 사례연구와 모의 실험을 통해서 일반적으로 믿어져왔던 것과는 달리 GEE 방법이 산포모수에 민감하게 영향을 받고 있음을 보였다. 특히 산포모수의 값이 일정하지 않은 경우에는 GEE 방법이 산포모수에 민감 하게 영향을 받고 있음을 보였다. 특히 산포모수의 값이 일정하지 않은 경우에는 GEE 방법에서 밝혀진 회귀모수 추정량의 일치성에도 문제가 발생할 수 있음을 보였다.

• The Korean Journal of Applied Statistics
• /
• v.12 no.1
• /
• pp.97-107
• /
• 1999

프로파일 분석은 반복측정 자료를 분석하는데 있어서 널리 사용되는 다변량 분석모형이다. 프로파일 분석에서는 처리 그룹간의 비교와 반응 프로파일의 평행성 검정을 위해서 4가지 검정통계량이 널리 사용되고 있다. 이들 검정통계량은 Wilks의 통계량($\Lambda$), Pillai's Trace 통계량(V), Hotelling-Lawley Trace 통계량(U), Roy's Maximum Root 통계량($\Theta$ )이다. 그 동안 이들 통계량들을 비교하기 위한 여러 연구가 있었지만 주로 일반적인 다변량 분산분석 모형에 근거한 비교였다. 본 논문에서는 자료가 반복측정 자료이고 우리의 관심이 프로파일 분석에 있을 때에 이 4가지 통계량의 비교에 초점을 맞추었다.

• The Korean Journal of Applied Statistics
• /
• v.11 no.2
• /
• pp.205-219
• /
• 1998

Statistical analyses have been perf7rm7d to find factors affecting chronic renal allograft dysfunction for 114 renal transplanted patients. Renal function was evaluated using serum creatinine values every three months during 1 year to 5 years after transplantation. Statistical models for the repeated measures were considered to evaluate factors affecting the reciprocal of serum creatinine values. This paper focuses on some common problems on the choice of correlation matrices occurred in the analysis of repeated measures.

• Journal of the Korean Data and Information Science Society
• /
• v.7 no.1
• /
• pp.129-135
• /
• 1996

본 논문은 의뢰인의 Pilot Study를 상담한 것으로서 당뇨병 및 암 환자에게 효능이 있는 약으로 밝혀진 Steroid계통의 Methyl Prednisolone이 척수손상 환자에게 효능이 있는지를 알아보기 위해, 토끼를 실험대상으로 하여 얻은 반복측정자료를 분석하였다.

• The Korean Journal of Applied Statistics
• /
• v.10 no.1
• /
• pp.189-201
• /
• 1997

The primary purpose of this study is to develop a measure of tracking by using a modified kappa statistic. Understanding tracking phenomena in epidemiologic studies is quite important, because precautionary measure can be made in the early stage of the outcome event. Several authors proposed measures of tracking. Among them we compared ours against McMahan's using a simulation study. Finally we applied our procedure and McMahan's to real data. We may conclude that our statistic is adequate in explaining and detecting the tracking phenomenon.

• Communications for Statistical Applications and Methods
• /
• v.16 no.6
• /
• pp.945-957
• /
• 2009

Repeated measurement data among several treatments with a control is often used in the field of medicine study. In this paper, we suggest a method for comparison of the linear trend of responds followed time among several treatments with a control based on repeated measurement data. First, we estimate slope from each subject and generate samples using the slope estimated previous. And then, we test the difference among treatment with a control by ANOVA F test, Jonckheere-Terpstra test, updated control group procedure using generated samples. Monte Carlo Simulation is adapted to compare the power and experimental significance levels in various configuration.

• 대한예방의학회:학술대회논문집
• /
• 2004.07a
• /
• pp.21-37
• /
• 2004

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.5
• /
• pp.1055-1067
• /
• 2017

Most previous works to study for the depression of the disabilities in Korea have analyzed the repeated measured data of each individual under the mutually independent assumption. In this study, Korea Welfare Panel data of the disabilities surveyed additionally every three years are analyzed to detect the significant exploratory variables by the linear mixed models. A suitable correlation matrix is considered for the dependency of repeated measurement of each individual. The random effect to reflect the characteristics of the individuals as well as the fixed effect is included in the fitted linear mixed model. By the residual plot of the fixed effect model, the problem that the averages of residuals of each individual do not seem to be around zero is described. Further, the residual plot and the Q-Q plot coming from the selected final model are shown that the problem is modified well.

• The Korean Journal of Applied Statistics
• /
• v.30 no.2
• /
• pp.203-213
• /
• 2017

We study estimation and inference of joint conditional distributions of bivariate longitudinal outcomes using regression models and copulas. We consider a class of time-varying transformation models and combine the two marginal models using Gaussian copulas to estimate the joint models. Our models and estimation method can be applied in many situations where the conditional mean-based models are inadequate. Gaussian copulas combined with time-varying transformation models may allow convenient and easy-to-interpret modeling for the joint conditional distributions for bivariate longitudinal data. We apply our method to an epidemiological study of repeatedly measured bivariate cholesterol data.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.6
• /
• pp.1263-1272
• /
• 2014

Longitudinal categorical data commonly occur from medical, health, and social sciences. In these data, the correlation of repeated outcomes is taken into account to explain the effects of covariates exactly. In this paper, we introduce marginalized random effects models that are used for the estimation of the population-averaged effects of covariates. We also review how these models have been developed. Real data analysis is presented using the marginalized random effects.