• The Korean Journal of Applied Statistics
• /
• v.30 no.5
• /
• pp.793-808
• /
• 2017

We compare various variable screening methods on multiclass classification problems when the data is ultrahigh-dimensional. Two different approaches were considered: (1) pairwise extension from binary classification via one versus one or one versus rest comparisons and (2) direct classification of multiclass responses. We conducted extensive simulation studies under different conditions: heavy tailed explanatory variables, correlated signal and noise variables, correlated joint distributions but uncorrelated marginals, and unbalanced response variables. We then analyzed real data to examine the performance of the methods. The results showed that model-free methods perform better for multiclass classification problems as well as binary ones.

• Communications for Statistical Applications and Methods
• /
• v.25 no.5
• /
• pp.489-499
• /
• 2018

Jeonse is a unique property rental system in Korea in which a tenant pays a part of the price of a leased property as a fixed amount security deposit and gets back the entire deposit when the tenant moves out at the end of the tenancy. Jeonse deposit is very important in the Korean real estate market since it is directly related to the residential property sales price and it is a key indicator to predict future real estate market trend. Jeonse deposit data shows a skewed and heteroscedastic distribution and the commonly used mean regression model may be inappropriate for the analysis of Jeonse deposit data. In this paper, we apply a Bayesian quantile regression model to analyze Jeonse deposit data, which is non-parametric and does not require any distributional assumptions. Analysis results show that the quantile regression coefficients of most explanatory variables change dramatically for different quantiles. The regression coefficients of some variables have different signs for different quantiles, implying that even the same variable may affect the Jeonse deposit in the opposite direction depending on the amount of deposit.

• Journal of Home Health Care Nursing
• /
• v.22 no.1
• /
• pp.109-116
• /
• 2015

Purpose: This study aimed to understand the elderly's sexuality by analyzing the relationship between subjective quality of life and perception, attitude, and coping behaviors regarding sexuality in the elderly. Methods: The participants were 120 indivisuals, aged 65 or over, located in Y city. Data were collected from April to June, 2012 by a questionnaire survey. Data analysis was done by using SPSS WIN 18.0 program including one-way ANOVA, independent t-test, Pearson correlation coefficients, and stepwise multiple regression. Results: The predicting variable affecting subjective quality of life was sexuality perception (B=0.45, p<.001), and sexual coping behavior (B=0.25, p=.014) and they have a 25.0%(Adj $R^2=25.0$) explanatory power for the subjective quality of life in the elderly. Conclusion: To increase the subjective quality of life for the elderly, it is necessary for the individuals to have a positive perception of their sexuality and the expression of positive sexual coping behavior.

• Journal of Environmental Impact Assessment
• /
• v.21 no.2
• /
• pp.265-277
• /
• 2012

This paper is primarily intended to present quantitative evidences for land surface albedo difference among seven metropolitan cites in South Korea. An empirical study for experimental sites was conducted to confirm how a standard MODerate Resolution Imaging Spectroradiometer (MODIS) instrument offers the viable method of measuring and comparing the regional heterogeneity of albedo among administrative districts. The metropolitan cities like Seoul located in dense building environment do result in much lower albedo than those exposed in much more sub-urban surface (e.g KwangJoo). These experimental results indicate that an urban surface such as building and road is a crucial explanatory variable for lower albedo. It is confirmed that the urban surface such as building and road could be employed as a proxy of the lower albedo burden in the metropolitan area. It is anticipated that this research output could be used as a valuable reference to confirm the potential of introducing the new concept of "administrative districts specific albedo management" to support more scientific and objective decision-making in the process of GHG (Greenhouse Gas) reduction project.

• Journal of Environmental Impact Assessment
• /
• v.20 no.2
• /
• pp.175-185
• /
• 2011

It is usual for energy consumption in accordance with facing and sitting direction of tower-type apartments to be calculated by the official statistics or computer simulation. Previous studies for energy consumption appear to be very limited due to the dependence on flat type of apartment. Acknowledging these constraints, an empirical study for a tower type apartment was conducted to demonstrate how a on-site indoor temperature measurement in spring can be used to assist in estimating the total energy consumption in terms of facing and sitting orientation specific settings. The results indicate that maximum temperature difference in spring was identified as $1.16^{\circ}C$ between south and eastern direction. It is known that raising $1^{\circ}C$ indoor temperature require 7% more energy consumption than normal. The $1.16^{\circ}C$ difference means that sitting direction of tower type apartment is a crucial explanatory variable as unit of analysis for energy consumption. It was demonstrated that the indoor temperature could be used effectively as an indicator to estimate energy consumption among various sitting direction of tower type apartments. It is anticipated that this research output could be used as a valuable reference to support more scientific and objective decision-making for facing and sitting orientation of tower type apartments.

• Journal of the Korean Home Economics Association
• /
• v.28 no.4
• /
• pp.87-101
• /
• 1990

This study was undertaken to test to fit forms of the Engel curves to data. The comparisons were confined to the linear, semi-logarithmic and double-logarithmic forms. Data from the 1970-1987 Urban Household Economy Survey were used to estimate the Engel curves. The twelve categories of consumption expenditure were considered for investigation. Parameters of the Engel curves were derived from OLS and TSLS. In this paper the size of the family was used as the deflater. The results could be summarized as follows: 1. Comparing with the R2 of three foms, it could be concluded that, the linear form generally gave a better fit to data than the other forms did. Only for housing and clothing and foot wear, did the semi-logarithmic form give a better fit. Only for meals outside the home, fuel, light and water charges, and miscellaneous, did the double-logarithmic form give a better fit. 2. Comping with the income elasticities based on the alternative forms, it could be concluded that the differences between the estimates were since each form made different assumption as to the way in which elasticity varied. In general, the semi-logarithmic form gave the highest estimate and double-logarithmic form did the lowest estimate. The difference between semi-logarithmic and the other forms were greater than the those of linear and double-logarithmic form. 3. It was found that the income elasticity varied with the difinition of income used as an explanatory variable in Engel curves.

• Korean Parent-Child Health Journal
• /
• v.15 no.2
• /
• pp.51-59
• /
• 2012

Purpose: The purpose of this study was to identify factors influencing health promoting behavior of school-aged children on community child center. Methods: Participant were 207 elementary school student located in Mokpo. For data analysis descriptive statistics, t-test, ANOVA pearson correlation coefficients and stepwise multiple regression were used with SPSS/WIN ver 18.0 program. Results: The mean score for health promoting behavior was below the lower point at $3.39{\pm}0.61$. There were significant differences in health promoting behavior according to gender (t=9.41, p=.002), father's job (F=2.28, p=.048), perceived health status (F=5.70, p=.001), There were significant correlations between health promoting behavior and self-esteem (r=.655, p=.001), self-efficacy (r=.530, p=.001). The explanatory power of these variables accounted for 47.1% of health promoting behavior. The most significant variable was self-esteem (t=7.60, p=.001) and explained 42.8%. Conclusion: The finding indicate that self-esteem of children on community child center are important variables for health promoting behavior. This result suggests that interventions focusing on self-esteem, on enhance health promoting behavior.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.8
• /
• pp.151-159
• /
• 2020

This study aims to determine the factors influencing the community behavior in improving competitive rural tourism as well as understanding the role of economic literacy in mediating socio-economic indicators and rural competitive advantage. This research followed an explanatory research to examine the relationship between variables including socio-economic variables and rural tourism competitive advantage. The data was gathered by conducting observations and interviews with tourism businesses, stakeholders, and the local village government, and related agencies as respondents. Furthermore, the data were analyzed following inductive and descriptive statistics. The findings indicated that, from all variables used, solely the environmental impact variable did not affect economic literacy and the competitive advantage of rural tourism. The moderating variables showed that the economic literacy mediates the economic impact on rural tourism competitive advantage. In addition, socio-cultural impacts on rural competitive advantage tourism, and the stakeholder involvement affects rural competitive advantage tourism. However, economic literacy failed in mediating between environmental impacts on rural competitive advantage tourism. This is due to the increasing understanding of the economy of the community around the tourist attractions it will increase the business around the tourist attractions that have an impact on environmental damage around the tourist attractions.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.10
• /
• pp.391-399
• /
• 2020

This study aims to analyze the relationship of e-HRM implementation to employee performance both directly and indirectly through the intervening of the Human Resource service Quality variable, both practically and theoretically. This study uses variance-based structural equation modeling (SEM) techniques with partial least square (PLS) statistical testing tools to test the direct relationship of e-HRM and the performance and relationship moderated by Human Resources service quality tested on 200 civil servants in five offices under the coordination of the Government of the South Sulawesi Province of Indonesia. The data collection model in this study uses an online survey. The data analysis stages through the explanatory concept consist of, first, the interpretation of the distribution of the average frequency of respondents' answers; second, outer-loading; third, determination of the validity and reliability; fourth, the coefficient of determination test and partial test; fifth, the GoF model; sixth, validity test; and seventh, hypothesis testing. This study explores four hypotheses in a comprehensive fashion; the results of this study show that all hypotheses have positive and significant effects both through direct and intervening relationships. Among the three direct relationships, the relationship of e-HRM variables on HR Service Quality is greatest and most dominant.

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.1
• /
• pp.125-133
• /
• 2013

In this paper, penalized binary logistic regression models are employed as statistical models for determining the discharge of 668 patients with a chief complaint of dyspnea based on 11 blood tests results. Specifically, the ridge model based on $L^2$ penalty and the Lasso model based on $L^1$ penalty are considered in this paper. In the comparison of prediction accuracy, our models are compared with the logistic regression models with all 11 explanatory variables and the selected variables by variable selection method. The results show that the prediction accuracy of the ridge logistic regression model is the best among 4 models based on 10-fold cross-validation.