• Journal of the Korean Data and Information Science Society
• /
• 제24권6호
• /
• pp.1409-1419
• /
• 2013

최근 종단자료 분석방법으로 많이 연구되는 잠재성장모형으로 청소년 패널자료를 분석하였다. 본 연구에서 잠재성장모형 분석에서 비조건적 모형을 좀 더 빠르게 찾기 위해 비조건적 모형에 반복측정 분산분석의 결과를 활용하였다. 또한, 비조건적 모형을 결정하기 위해 기존에 주로 사용된 6개 유형, 2차모형과 반복측정분산분석의 결과를 적용한 모형들을 비교하였다.

• 응용통계연구
• /
• 제15권2호
• /
• pp.337-354
• /
• 2002

본 논문에서는 오차성분이 계열상관을 갖는 불균형 랜덤모형에서 분산성분의 추정방법에 대하여 연구하였다. 분산성분에 대한 추정량으로 조건부 ANOVA(cANOVA), ML및 REML추정량등을 유도하였으며, 계열상관값과 불균형의 정도에 따른 추정량의 변동성을 추정량의 분위수를 이용하는 EQDGs플롯을 이용하여 비교하였다. 모의실험결과 cANOVA추정방법은 불균형의 정도에는 추정량값이 크게 영향을 받지 않는 것으로 나타났으나 계열상관값의 증가에 따라서는 변동성을 보이고 있다. 불균형의 정도와 계열상관값을 동시에 고려하는 경우에는 ML추정방법이 cANOVA, REML추정방법보다 변동성이 안정적으로 나타났다.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회/대한산업공학회 2005년도 춘계공동학술대회 발표논문
• /
• pp.975-982
• /
• 2005

The purpose of the Gage R&R study is to determine whether a measurement system is adequate for monitoring a process. If the measurement system variation is small relative to the process variation, then the measurement system is deemed 'adequate'. The sources of variation associated with the measurement system are compared using an analysis of variance (ANOVA) model, in general. A typical ANOVA model used in a standard Gage R&R study is the two-factor random effect model. Then, the ANOVA partitions the total variation into three categories: repeatability, reproducibility, part variation. However, if the process variation possesses the between group variation, within group variation, and within-part variation, these variations can cause the measurement system evaluation to provide misleading results. That is, in the standard Gage R&R study these variations affect the estimate of repeatability, reproducibility, or both. This paper presents a four-factor nested factorial ANOVA model which explicitly considers these variations for the Gage R&R study. The variance component estimates are derived by setting the EMS equations equal to the corresponding mean square from the ANOVA table and solving. And the proposed model is compared with the standard Gage R&R model.

• 산업공학
• /
• 제18권4호
• /
• pp.444-453
• /
• 2005

The purpose of the Gage R&R study is to determine whether a measurement system is adequate for monitoring a process. If the measurement system variation is small relative to the process variation, then the measurement system is deemed "adequate". The sources of variation associated with the measurement system are compared using an analysis of variance (ANOVA) model, in general. A typical ANOVA model used in a standard Gage R&R study is the two-factor random effect model. Then, the ANOVA partitions the total variation into three categories: repeatability, reproducibility, part variation. However, if the process variation possesses the between group variation, within group variation, and within part variation, these variations can cause the measurement system evaluation to provide misleading results. That is, in the standard Gage R&R study these variations affect the estimate of repeatability, reproducibility, or both. This paper presents a four-factor nested factorial ANOVA model which explicitly considers these variations for the Gage R&R study. The variance component estimators are derived by setting the EMS equations equal to the corresponding mean square from the ANOVA table and solving. And the proposed model is compared with the standard Gage R&R model.

• Journal of the Korean Data and Information Science Society
• /
• 제13권2호
• /
• pp.317-328
• /
• 2002

We first derive group ordering reference priors in a two-way mixed-effects analysis of variance (ANOVA) model. We show that posterior distributions are proper and provide marginal posterior distributions under reference priors. We also examine whether the reference priors satisfy the probability matching criterion. Finally, the reference prior satisfying the probability matching criterion is shown to be good in the sense of frequentist coverage probability of the posterior quantile.

• 한국생물정보학회:학술대회논문집
• /
• 한국생물정보시스템생물학회 2001년도 제2회 생물정보 워크샵 (DNA Chip Bioinformatics)
• /
• pp.97-115
• /
• 2001

cDNA microarray technology allows the monitoring of expression levels for thousands of genes simultaneously. Many statistical analysis tools become widely applicable to the analysis of cDNA microarray data. In this talk, we consider a two-way ANOVA model to differentiate genes that have high variability and ones that do not. Using this model, we detect genes that have different gene expression profiles among experimental groups. The two-way ANOVA model is illustrated using cDNA microarrays of 3,800 genes obtained in an experiment to search for changes in gene expression profiles during neuronal differentiation of cortical stem cells.

• Journal of the Korean Statistical Society
• /
• 제35권3호
• /
• pp.317-329
• /
• 2006

In the problem of estimating the error variance in the balanced fixed- effects one-way analysis of variance (ANOVA) model, Ghosh (1994) proposed hierarchical Bayes estimators and raised a conjecture for which all of his hierarchical Bayes estimators are admissible. In this paper we prove this conjecture is true by representing one-way ANOVA model to the distributional form of a multiparameter exponential family.

• 응용통계연구
• /
• 제15권2호
• /
• pp.405-414
• /
• 2002

반복이 같은 이원배치 혼합효과 분산분석모형에서 무정보 사전분포를 이용하여 오차분산을 추정하는 문제를 생각하고자 한다. 먼저 무정보 사전분포로 제프리스사전분포, 준거 사전분포 그리고 확률일치 사전분포를 유도하고 이들 각각의 사전분포들에 대하여 주변사후분포를 제시하였다. 끝으로 실제 자료를 근거로 오차분산의 주변사후밀도함수에 대한 그래프와 오차분산에 대한 신용구간들을 구하고 이 구간들을 비교한다.

• Communications for Statistical Applications and Methods
• /
• 제8권3호
• /
• pp.667-675
• /
• 2001

The usefulness of analysis of variance(ANOVA) estimates of variance components is impaired by the frequent occurrence of negative values. The probability of such an occurrence is therefore of interest. In this paper, we investigate a variety of reasons for negative estimates under one way random effects model. It can be shown, through simulation, that this probability increases when the number of treatments is too small for fixed total observations, unbalancedness of data is severe, ratio of variance components is too small, and data may contain many outliers.

• 대한안전경영과학회:학술대회논문집
• /
• 대한안전경영과학회 2009년도 추계학술대회
• /
• pp.557-563
• /
• 2009

The research develops measurement processes for estimating and evaluating the gauge R&R(Reproducibility & Repeatability) using ANOVA(Analysis of Variance) of experimental design tools. The ten-step processes developed include experimental goal setting, the selection of characteristics(factors, levels), data model, ANOVA, EMS(Expected Mean Square), estimation of gauge precisions, and evaluation indexes. The three-factor combined measurement models are presented to show the processes developed in this paper.