• Journal of the Korean Data and Information Science Society
• /
• v.17 no.2
• /
• pp.661-668
• /
• 2006

There have been some controversies on the use of the coefficient of determination for linear no-intercept model. One definition of the coefficient of determination, $R^2={\sum}\;{\widehat{y^2}}\;/\;{\sum}\;y^2$, is being widely accepted only for linear no-intercept models though Kvalseth (1985) demonstrated some possible pitfalls in using such $R^2$. Main objective of this note is to report that $R^2$ is not a desirable measure of fit for the no-intercept linear model. In fact it is found that mean square error(MSE) could replace $R^2$ efficiently in most cases where selection of no-intercept model is at issue.

• 한국데이터정보과학회:학술대회논문집
• /
• 2005.04a
• /
• pp.145-154
• /
• 2005

There have been some controversies on the use of the coefficient of determination for linear no-intercept model. One definition of the coefficient of determination, $R^2=\sum\;{y}{^{\hat{2}}/\sum\;{y^2}$, is being widely accepted only for linear no-intercept models though Kvalseth(1985) demonstrated some possible pitfalls in using such $R^2$. Main objective of this article is to provide a cautionary notice for use of the $R^2$ by pointing out its tricky aspects by means of empirical simulations.

• Communications for Statistical Applications and Methods
• /
• v.26 no.6
• /
• pp.539-556
• /
• 2019

This paper derive a method to solve change point regression problems via a process for obtaining consequential results using properties of a difference-based intercept estimator first introduced by Park and Kim (Communications in Statistics - Theory Methods, 2019) for outlier detection in multiple linear regression models. We describe the statistical properties of the difference-based regression model in a piecewise simple linear regression model and then propose an efficient algorithm for change point detection. We illustrate the merits of our proposed method in the light of comparison with several existing methods under simulation studies and real data analysis. This methodology is quite valuable, "no matter what regression lines" and "no matter what the number of change points".

• Journal of the Korean Society of Child Welfare
• /
• no.40
• /
• pp.41-71
• /
• 2012

The purpose of this study is to examine longitudinal impacts of various factors on happiness in primary school children. Specifically, attachment theory and ecosystems perspective were utilized for the purpose of this study. We used Korea Youth Panel Survey, which is a 5-year longitudinal data collected from fourth grade in elementary school to second grade in middle school Latent growth model was employed as the analytic method. The findings of this study are as follow: first, academic achievement, self-esteem, parent attachment, peer attachment, teacher attachment, and community attachment all decreased over the 5-year study period. Also, the intercept and the slope variance of variables were found to be statistically significant. This means that there are significant differences in the intercept and the slope of individuals. Second, self-esteem, parent attachment, and peer attachment were found to have cross-sectional influences on happiness. This means that self-esteem, parent attachment, and peer attachment are positively associated with happiness at the intercept. Also, self-esteem, parent attachment, teacher attachment, and community attachment were found to have longitudinal influences on happiness. This means that the higher levels of community attachment at the intercept is associated with slower the rate of decrease in happiness at the slope. In addition, faster rates of decrease in self-esteem, parent attachment, teacher attachment, and community attachment are associated with faster the rate of decrease in happiness. Third, this study conducted multiple group analysis with gender. The findings of this analysis revealed no significant differences in analytic models between males and females. Based on these findings, theoretical and practice implications with regard to happiness in primary school children are discussed.

• Journal of Science Education
• /
• v.46 no.1
• /
• pp.80-92
• /
• 2022

We fitted latent growth models of attitude towards science using the Korea Education & Employment Panel 2004-2007 data with 343 high school students. The growth model show better fit indices compared to the no growth model. The intercept and slope showed significant variances, and thus, we added control variables of the number, ratio of advanced courses, and variety in science elective subjects, and the achievement percentile for middle school. In the conditional growth model, the previous achievement has significant positive effects on the intercept and the ratio of the advanced courses and variety of science subjects show significantly positive effects on the slope. Based on the results, it supports the 2022 Revised Science Curricular that high school credit system should provide students with basic 'Physics,' 'Chemistry,' 'Biology,' and 'Earth Science,' credits in 'general electives', various integrated subjects in 'converged electives', and highly advanced subjects in 'career electives.'

• Korean Journal of Ecology and Environment
• /
• v.41 no.4
• /
• pp.457-465
• /
• 2008

The purpose of the study was to evaluate spatial and temporal dynamics of nutrients (TN, TP), organic pollution (BOD, COD), and ionic dynamics (electrical conductivity, EC) in the North Han-River, South Han-River, and merged downriver using the dataset of $1998{\sim}2007$, obtained from the MEK (Ministry of Environment, Korea). Accord. ing to interannual nutrient analysis, TN varied slightly in the North Han-River and South Han-River, but decreased in the merged downriver along with BOD. Longitudinal analysis in the water quality showed that BOD, COD, and nutrients had linear decreasing trend along the main axis of headwater-to-downriver. Concentrations of TP and TN in the North Han-River averaged $26.97{\mu}g\;L^{-1}$, $1.696mg\;L^{-1}$, respectively, which were minimum in the three watersheds, followed by South Han-River and then the merged downriver in order. Ratios of TN:TP in the watersheds were >40 in all the sites, indicating that nitrogen may be enough for periphyton or phytoplankton growth and phosphorus may be limited partially. After the North Han-River water is merged with South Han-River, the concentrations of BOD, COD, TN, and TP were similar to the values of $S6{\sim}S7$, respectively or a little bit higher, but increased abruptly in Site M4 (Fig. 3). Thus, mean values of all the water quality parameters in the reach of $M4{\sim}M7$ sites were greater than any other sites. Seasonal data analysis indicated that BOD and EC in the downstream ($S3{\sim}S7$) was greater in the premonsoon than two seasons of the monsoon and postmonsoon, and no significant differences in BOD between the three seasons were found in the upstream ($S1{\sim}S2$). Empirical models of COD in the merged downriver was predicted ($R^2=0.87$, p>0.01, slope = 0.84, intercept = -1.28) well by EC. These results suggest that EC to be measured easily in the field may be used for estimations of nutrients and organic matter pollutions in the merged downriver and these linear models are cost-effective for the monitoring of the parameters.

• Journal of the Korea Convergence Society
• /
• v.12 no.5
• /
• pp.313-326
• /
• 2021

This study was to introduce ecological momentary assessment and show how to apply it to real-world research. As preliminary study for sustainable development, the result explained growth model using senior's longitudinal data and suitability of multi-level model in EMA data with regression analysis. The total variance of dependent variable was determined through a base model with only intercept and approximately 47% of total variance was caused by individual differences and 53% by time point differences. Second model was used to verified that each individual has a different effect on the senior vitality and effect on time was not significant. This is because it is the result of a preliminary stage where treatment is not involved and there is no significant change in process of collecting EMA data without external intervention. Third model that add gender as an independent variable showed significant change in both time and gender. Finally compared the PRD for each model and found models that without gender variables fit the data more effectively. This suggests that studies dealing with longitudinal data such as EMA data should adopt multi-level model that can measure individual characteristics, taking into account respondents' time and context.