• Journal of the Korean Data and Information Science Society
• /
• v.13 no.2
• /
• 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.

• Communications for Statistical Applications and Methods
• /
• v.9 no.2
• /
• pp.315-324
• /
• 2002

For estimating the error variance under the relative squared error loss in two-way analysis of variance models, we provide a class of hierarchical Bayes estimators and then derive a subclass of the hierarchical Bayes estimators, each member of which dominates the best multiple of the error sum of squares which is known to be minimax. We also identify a subclass of non-minimax hierarchical Bayes estimators.

• The Korean Journal of Applied Statistics
• /
• v.15 no.2
• /
• pp.405-414
• /
• 2002

We consider the problem of estimating the error variance of in a two-way mixed-effects ANOVA model using noninformative priors. First, we derive Jeffreys' prior, a reference prior, and matching priors. We then provide marginal posterior distributions under those noninformative priors. Finally, we provide graphs of marginal posterior densities of the error variance and credible intervals for the error variance in two real data set and compare these credible intervals.

• Communications for Statistical Applications and Methods
• /
• v.6 no.2
• /
• pp.487-500
• /
• 1999

We propose a class of hierarchical Bayes estimators of the error variance under the relative squared error loss in balanced fixed-effects two-way analysis of variance models. Also we provide analytic expressions for the risk improvement of the hierarchical Bayes estimators over multiples of the error sum of squares. Using these expressions we identify a subclass of the hierarchical Bayes estimators each member of which dominates the best multiple of the error sum of squares which is known to be minimax. Numerical values of the percentage risk improvement are given in some special cases.

• Journal of Environmental Science International
• /
• v.16 no.11
• /
• pp.1209-1218
• /
• 2007

Advertisement signboards on the buildings have functionally a visual value as factor of urban and building design. But it is not easy to find any reasonable principles and regulations, how well the signboards deliver the information of stores to the customers, and how they contribute the visual amenity from the sight of urban landscape. Under this context, this study tries to analyze the information delivery power of signboards in relation to the visual cognition. The analysis method is the Two-Way ANOVA (Analysis of Variance) evaluation with factors, such as scale, amount and arrangement of signboards. The scale of letters or figures at Signboards is specified in 3 different sizes such as big, medium and small. The amount is classified into 5 grades from 100% to 20% installation. And the arrangement is divided into orderly and disorderly installation. As the results of the Two-Way ANOVA, the identical scale of signboards is much better for the awareness. And the orderly arrangement shows also the same result. Above all, including these two results, the 80% of installation showed the biggest different result of awareness.

• Restorative Dentistry and Endodontics
• /
• v.39 no.2
• /
• pp.143-147
• /
• 2014

• The Korean Journal of Applied Statistics
• /
• v.23 no.2
• /
• pp.317-323
• /
• 2010

Measures are very useful tools for comparing the shape variability in statistical shape analysis. For examples, the Procrustes statistic(PS) is isolated measure, and the mean Procrustes statistic(MPS) and the root mean square measure(RMS) are overall measures. But these measures are very subjective, complicated and moreover these measures are not statistical for comparing the shape variability. Therefore we need to study some tests. It is well known that the Hotelling's $T^2$ test is used for testing shape variability of two independent samples. And for testing shape variabilities of several independent samples, instead of the Hotelling's $T^2$ test, one way analysis of variance(ANOVA) can be applied. In fact, this one way ANOVA is based on the balanced samples of equal size which is called as BANOVA. However, If we have unbalanced samples with unequal size, we can not use BANOVA. Therefore we propose the unbalanced analysis of variance(UNBANOVA) for testing shape variabilities of several independent samples of unequal size.

• The Korean Journal of Applied Statistics
• /
• v.8 no.1
• /
• pp.75-87
• /
• 1995

Computer graphics approach is a powerful tool when we are to explore the effects of the change of a part of the data, or the effects of the alteration of the characteristics of the statistical model currently employed. The paper describes the methods to implement dynamic graphics for the process of analysis of variance, and the methods to graphically represent ANOVA type data. The paper the describes a dynamic graphics software developed by the author for two-way ANOVA model.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.35 no.3
• /
• pp.118-128
• /
• 2012

An attempt is given to the problem of analyzing the two-way binary attribute data using the logistic regression model in order to find a sound statistical methodology. It is demonstrated that the analysis of variance (ANOVA) may not be good enough, especially for the case that the proportion is very low or high. The logistic transformation of proportion data could be a help, but not sound in the statistical sense. Meanwhile, the adoption of generalized least squares (GLS) method entails much to estimate the variance-covariance matrix. On the other hand, the logistic regression methodology provides sound statistical means in estimating related confidence intervals and testing the significance of model parameters. Based on simulated data, the efficiencies of estimates are ensured with a view to demonstrate the usefulness of the methodology.

• Archives of Pharmacal Research
• /
• v.18 no.4
• /
• pp.237-242
• /
• 1995

For the vioequivalence study of two ceftriaxone injection formulations ($Rocephin{\circledR}$ ; Roche, and Triaxone ; Hanmi0, the HPLC analytical method for the analysis of ceftriaxone in plasma was used. Fourteen healthy volunteers completed the study and each subject were IM in jected signle doses (1 g) of the test and the reference formulations in a two-way crossover design with an one week drug free interval between doses. Following each administration, plasma concentrations of ceftrixone were monitored over a period of 24 h. Bioequivalence parameters $AUC_{24th}, {\;}T_{max}, {\;}C_{max}$ and MRT determined from the data obtained for the two formulations were examined by analyses of variance (ANOVA) and other criteria and tests for bioequivalence. Results of ANOVA and confidence limits of test/reference ratios of $AUC_{24th}, {\;}T_{max}, {\;}C_{max}$ and MRT, and statistical tests indicated the bioequivalence of the two formulations (i.e., test/reference ratio was within $100{\pm}20%$) except for $T_{max}$ The mean of $T_{max}$ showed only 6. 9% difference from the reference but the detection limit was 22.5% which is slightly over the 20% criteria. No pharmacokinetic parameters including Ka, Kel, Vd and Cl indicated significant difference in between the two fomulations. It was concluded that the data yielded fro the two cefriaxone formulations demonstrated that they were bioequivalent.