• Communications for Statistical Applications and Methods
• /
• v.10 no.2
• /
• pp.291-303
• /
• 2003

This work is proposed an alternative identification method of outlying cell which is one of important issues in categorical data analysis. One finds that there is a strong relationship between the location of an outlying cell and the corresponding parameter estimates of the well-fitted log-linear model. Among parameters of log-linear model, an outlying cell is affected by interaction terms rather than main effect terms. Hence one could identify an outlying cell by investigating of parameter estimates in an appropriate log-linear model.

• Archives of design research
• /
• v.15 no.3
• /
• pp.167-180
• /
• 2002

This study investigates effective ways to help users form a correct mental model of the hierarchical information space (HIS) in small display. The focus is the effect of color cue on understanding the structure and navigating the information space. The concept of color space (CS) corresponds well to the HIS - one color has a unique position in the CS as a piece of information does in HIS. In this study, we empirically examined two types of color cue, namely, categorical and depth cue. Hue was used as a categorical cue and tone was used as a depth cue. In our experiment, we evaluate the effectiveness of the color cues in the mobile internet system. Subjects were asked to perform four searching tasks and four comparison tasks. The results of experiment reveal that the categorical cues significantly improve the user's mental model whereas decrease navigation performances. The depth cues cannot aid in understanding the HIS as well as improve navigation performances. This study concludes with limitations of the study and descriptions of future studies.

• Proceedings of the Korean Statistical Society Conference
• /
• 2003.10a
• /
• pp.179-182
• /
• 2003

This study describes a new graphical method for assessing and characterizing effect modification by a matching covariate in matched case-control studies. This method to understand effect modification is based on a semiparametric model using a varying coefficient model. The method allows for nonparametric relationships between effect modification and other covariates, or can be useful in suggesting parametric models. This method can be applied to examining effect modification by any ordered categorical or continuous covariates for which cases have been matched with controls. The method applies to effect modification when causality might be reasonably assumed. An example from veterinary medicine is used to demonstrate our approach. The simulation results show that this method, when based on linear, quadratic and nonparametric effect modification, can be more powerful than both a parametric multiplicative model fit and a fully nonparametric generalized additive model fit.

• Journal of Integrative Natural Science
• /
• v.7 no.3
• /
• pp.208-213
• /
• 2014

National-wide and/or large scale sample surveys generally use complex sample design. Traditional Pearson chi-square test is not appropriate for the categorical complex sample data. Rao-Scott suggested an adjustment method for Pearson chi-square test, which uses the average of eigenvalues of design matrix of cell probabilities. This study is to compare the efficiency of Rao-Scott first order adjusted test to Wald test for homogeneity between two populations using 2009 Gyeongnam regional education offices's customer satisfaction survey (2009 GREOCSS) data. The 2009 GREOCSS data were collected based on stratified three-stage cluster sampling with probability proportional to size. The empirical results show that the Rao-Scott adjusted test statistic using only the variances of cell probabilities is very close to the Wald test statistic, which uses the covariance matrix of cell probabilities, under the 2009 GREOCSS data based. However it is necessary to be cautious to use the Rao-Scott first order adjusted test statistic in the place of Wald test because its efficiency is decreasing as the relative variance of eigenvalues of the design matrix of cell probabilities is increasing, specially more when the number of degrees of freedom is small.

• The Korean Journal of Applied Statistics
• /
• v.15 no.2
• /
• pp.297-310
• /
• 2002

Liang and Zeger proposed generalized estimating equations(GEE) for analyzing repeated data which is discrete or continuous. GEE model can be extended to model for repeated categorical data and its estimator has asymptotic multivariate normal distribution in large sample sizes. But GEE is based on large sample asymptotic theory. In this paper, we study the properties of GEE estimators for repeated ordinal data in small sample sizes. We generate ordinal repeated measurements for two groups using two methods. Through Monte Carlo simulation studies we investigate the empirical type 1 error rates, powers, relative efficiencies of the GEE estimators, the effect of unequal sample size of two groups, and the performance of variance estimators for polytomous ordinal response variables, especially in small sample sizes.

• Proceedings of the Korean Statistical Society Conference
• /
• 2002.11a
• /
• pp.293-298
• /
• 2002

We propose an improved version of Kim (2000) to the effect that in principle we may deal with a graphical model of any size. Kim (2000) proposed a method of estimating parameters for a model of categorical variables which is too large to handle as a single model. We applied the proposed method to a simulated data of 158 binary variables.

• Communications for Statistical Applications and Methods
• /
• v.11 no.3
• /
• pp.597-607
• /
• 2004

The primary interest of drug development studies is identifying the lowest dose level producing a desirable effect over that of the zero-dose control, which is referred as the minimum effective dose (MED). In this paper, we suggest a nonparametric procedure for identifying the MED with binary or ordered categorical response data. Proposed test and Williams' test are compared by Monte Carlo simulation study and discussed.

• Journal of Sport and Applied Science
• /
• v.4 no.4
• /
• pp.27-32
• /
• 2020

Purpose: This study sought to explore the effects of air pollution on professional sports in South Korea. Research design, data, and methodology: The dependent variable, the number of attendances, was comprised of 2013-2017 K-league, 2015-2017 KBO, 2014-2017 KBL regular season games, resulting in 1,063, 2,121, 810 individual match-level observations, respectively. With the actual data collected from each place across the country, we created a categorical variable which identify the air quality index divided into four categories by K-eco (i.e., good, moderate, unhealthy, hazardous). To analyze data, ANOVA was employed. Results: First, there was a significant group effect on K-league attendance. Second, there was a significant group effect of KBO attendance. Lastly, there was a significant group effect on KBL attendance. Conclusions: Summary of above results showed that each professional sport leagues' attendance was significantly different depending on the levels of air pollution. Implications were also discussed. Keywords: air pollution, sport spectatorship, professional sports.

• Journal of Digital Convergence
• /
• v.11 no.12
• /
• pp.93-100
• /
• 2013

This paper analyzes determinants of tourist consumption in the case of 2013 Gangneung Dano Festival, based on the multiple regression model. We set 12 determinants of consumption such as income as explanatory variables and consumption expenditure as a dependent variable. Also Five kinds of categorical consumptions are estimated. Main results are the followings. First, income is the most important factor and shows positive effect in tourist consumption. Second, age and metropolitan area influence consumption positively. Third number of participating day and length of stay also influence consumption positively. Fourth, number of accompanying person shows negative effect on consumption. Fifth, male, married person, and lodge with own expense influence consumption positively. Finally, categorical consumption has its specific determinants distinct from common factors This paper can be applied to invent and implement efficient strategies for development in regional economies and tour industries.

• Journal of Practical Engineering Education
• /
• v.14 no.3
• /
• pp.505-512
• /
• 2022

The purpose of this study is to synthesize effects of the living lab-based education through meta-analysis. Seven primary studies reporting the effect of living lab-based education were carefully selected for data analysis. Research questions are as follows. First, what is the overall effect size of the living lab-based education? The overall effect size refers to the effect on the cognitive and affective domains. Second, what is the effect size of the living lab-based education according to categorical variables? Categorical variables are outcome characteristics, study characteristics, and design characteristics. Results are summarized as follows. First, the overall effect size of living lab-based education was 0.347. Second, the effect size according to the cognitive domain was 1.244 for information process, 0.593 for communication, 0.261 for problem solving, and 0.26 for creativity. Third, the effect size according to subject area was shown in the order of electrical and electronic engineering 1.146, technology and home economics 0.489, artificial intelligence 0.379, and practical arts 0.168. Fourth, the effect size according to school level was 1.058 for high school, 0.312 for middle school, and 0.217 for elementary school. Fifth, the effect size by grade level was 0.295 when two or more grades were integrated and 0.294 for a single grade.