• The Korean Journal of Applied Statistics
• /
• v.35 no.5
• /
• pp.631-644
• /
• 2022

This paper considers robust estimation of the sparse vector autoregressive model (sVAR) useful in high-dimensional time series analysis. First, we generalize the result of Xu et al. (2008) that the adaptive lasso indeed has robustness in sVAR as well. However, adaptive lasso method in sVAR performs poorly as the number and sizes of outliers increases. Therefore, we propose new robust estimation methods for sVAR based on least absolute deviation (LAD) and Huber estimation. Our simulation results show that our proposed methods provide more accurate estimation in turn showed better forecasting performance when outliers exist. In addition, we applied our proposed methods to power usage data and confirmed that there are unignorable outliers and robust estimation taking such outliers into account improves forecasting.

• Information Systems Review
• /
• v.19 no.1
• /
• pp.123-145
• /
• 2017

This study empirically examines the effects of regulation on online gaming. Going beyond ad hoc heuristic approaches on individual behavior, we investigate the effects of regulation on dynamic changes of games or service providers. In particular, we propose three theoretical perspectives: social influence to investigate the regulation effect, the role of prior experience to determine the difference in the regulation effect size through users' prior experience, and network externalities to discover the difference in the regulation effect size according to the number of users on an online gaming platform. We use the vector autoregression methodology to model patterns of the co-movement of online games and to forecast game usage. We find that online gamers are heterogeneous. Therefore, policy makers should make suitable regulations for each heterogeneous group to effectively avoid generating gaming addicts without interrupting the economic growth of the online gaming industry.

• Journal of Korea Port Economic Association
• /
• v.40 no.2
• /
• pp.1-20
• /
• 2024

The purpose of this study is to clarify a safety efficiency of ports in South Korea considering port casualties. The paper conducted a vector auto regression to analyze a cause-and-effect relationship between latent factors and port casualties. Subsequently, the paper evaluated safety efficiency for the ports using an undesirable outputs model. The results implied that the number of workers in the shipping union had a statistical effect on the port casualties. In contrast, the number of workers in the operators and working hours are unrelated to the port casualties. In addition, it was found that Yeosu Gwangyang Port is the most safety efficiency port in South Korea. Based on these results, this paper may provide various policy implications for port operators, developers, and managers.

• Industry Promotion Research
• /
• v.5 no.1
• /
• pp.99-106
• /
• 2020

The purpose of this study was to analyze the effects of name attractiveness on self-efficacy and emotional awareness in adult men and women. The subjects of this study were 300 males and females in their 10s and 30s living in the metropolitan area. However, 250 copies, excluding missing questionnaires during the collection process and incomplete questionnaires, were used for the analysis. As a result of analyzing the difference in name attractiveness according to factors, the lower the age group and the lower the academic level, the more dissatisfied they were with their names. Besides, the regression analysis conducted to verify the effect of name attractiveness on self-efficacy showed that the model's fitness was R²=.382 and the model's explanatory power was somewhat inferior, but β=.322, t-value 9.276, p<.001 were shown to be statistically significant, so name attraction directly affects self-efficacy. And the results of the regression analysis conducted to verify the effect of name attractiveness on emotionality turned out to be R²=.412. The regression analysis, which controls demographic variables such as gender, age, and academic level, was statistically significant as β=.326, t-value 6.408, p<.001. In other words, the name attractiveness affects emotional awareness. There is no empirical study that the name attractiveness can improve happiness or the quality of life, but it seems often among athletes that names are enhanced by the past.

• The Journal of the Korea Contents Association
• /
• v.13 no.11
• /
• pp.1036-1045
• /
• 2013

The purpose of this study was to examine the effects of Simulation as a Problem-Based Learning (S-PBL) on critical thinking disposition, self-efficacy, and learning attitude and to compare an ordinary least square and a quantile regression method in impacting factors on critical thinking disposition. 143 students from six classes were randomly selected from a total of ten fundamental classes were assigned 66 in the control group and 77 in the experimental group. The results were that the experimental group received S-PBL and improved their critical thinking disposition and self-efficacy compared to the traditional learning method. In ordinary least square, affecting factors on critical thinking were the learning method and self-efficacy and these variables explained 41.0% in the critical thinking disposition. The results of the quantile regression method showed that affecting factors of critical thinking disposition were learning attitude of 0.1 quantile to 0.7 quantile and self-efficacy of all quantiles, and learning attitude of 0.4, 0.6, and 0.7 quantiles. Conclusion: The S-PBL is an effective method for nursing students who have low critical thinking disposition score to increase critical thinking disposition. And instructors can actively use S-PBL to enhance critical thinking disposition as well as self-efficacy in class.

• Korean Journal of Social Welfare Studies
• /
• v.43 no.1
• /
• pp.5-29
• /
• 2012

The present study was to explore what makes adolescents think of themselves as troublemakers even without conduct problems. It was expected that the failure to attain socio-developmental milestones(e.g., healthy relationships with others, academic achievement) would lead to form trait aspect of deviant self-concept. A latent state-trait autoregressive modeling was used to analyze five annual waves of data from 3,449 adolescents taken from the Korean Youth Panel Study. We decomposed trait and state aspect of deviant self-concept and identified significant predictors of trait-like deviant self-concept, while additionally testing for gender differences. Our results showed that conduct problems had greater effect on deviant self-concept among girls compared with boys. Conduct problem was most predictive of deviant self-concept, and yet both poor peer-relations and school failures predisposed adolescents to have deviant self-concept. Low academic achievement conferred risk for trait aspects of deviant self-concept with no gender difference, whereas poor peer relation was more predictive among girls. It highlights the cultural value system underlying self-concept and how and why adolescents think of themselves as troublemakers.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.1
• /
• pp.640-645
• /
• 2021

The deep learning based end-to-end TTS system consists of Text2Mel module that generates spectrogram from text, and vocoder module that synthesizes speech signals from spectrogram. Recently, by applying deep learning technology to the TTS system the intelligibility and naturalness of the synthesized speech is as improved as human vocalization. However, it has the disadvantage that the inference speed for synthesizing speech is very slow compared to the conventional method. The inference speed can be improved by applying the non-autoregressive method which can generate speech samples in parallel independent of previously generated samples. In this paper, we introduce FastSpeech, FastSpeech 2, and FastPitch as Text2Mel technology, and Parallel WaveGAN, Multi-band MelGAN, and WaveGlow as vocoder technology applying non-autoregressive method. And we implement them to verify whether it can be processed in real time. Experimental results show that by the obtained RTF all the presented methods are sufficiently capable of real-time processing. And it can be seen that the size of the learned model is about tens to hundreds of megabytes except WaveGlow, and it can be applied to the embedded environment where the memory is limited.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.5
• /
• pp.277-287
• /
• 2024

The purpose of this study was to explore the predictors of self-compassion correlated to mental health, and to suggest integrated self-compassion training and mental health practice plans for social welfare college students. Although self-compassion has been shown to be an important predictor in maintaining personal mental health, research on practical knowledge to improve level of self-compassion is limited. Therefore, there is a need to explore the relationship between predictors related to self-compassion for suggesting alternative interventions. This study used resilience, mental health well-being, and engagement scales whose relationships have been explored in self-compassion studies. Data was collected for 2021-2022 from third-year or higher social welfare college students in the metropolitan area. A total of 202 cases were analyzed, and correlation and regression analysis were applied using SPSS. Self-compassion was positively correlated with resilience, mental health well-being, and engagement. Resilience and mental health well-being were identified as important predictors of self-compassion. Unlike self-compassion, resilience and mental health well-being are familiar with social welfare students and educators, and existing resilience training and well-being education would be integrated to improve self-compassion capability.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.8
• /
• pp.3786-3793
• /
• 2013

This study aimed to investigate the influence of self-image, and self-esteem of 119 Rescue workers in D city on job satisfaction. This research design was a descriptive study. Data were collected from November 19, 2012 to December 08, 2012, analyzed by SPSS 20.0 program. There were statistical difference between age, period of employment, position, and license and self-image. There were statistical difference between age, position, license and self-esteem. There were statistical differences between age, period of employment, position and job satisfaction. Job satisfaction was positively related to self-image and self-esteem. In the multivariate regression analysis, adjusted R2 value was 0.268. It is necessary to enhance the career and awareness of job satisfaction of 119 rescue workers.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.35 no.3
• /
• pp.216-222
• /
• 2002

Autocorrelation in time series data can affect statistical inference in correlation or regression analyses. To improve a regression model from which the residuals are autocorrelated, Yule-Walker method, nonlinear least squares estimation, maximum likelihood method and 'prewhitening' method have been used to estimate the parameters in a regression equation. This study reviewed on the estimation methods of preventing spurious correlation in the presence of autocorrelation and applied the former three methods, Yule-Walker, nonlinear least squares and maximum likelihood method, to a 20-year real data set. Monte carlo simulation was used to compare the three parameter estimation methods. However, the simulation results showed that the mean squared error distributions from the three methods simulated do not differ significantly.