• The Korean Journal of Applied Statistics
• /
• v.34 no.6
• /
• pp.937-944
• /
• 2021

The problem of selecting variables is addressed in partial linear regression. Model selection for partial linear models is not easy since it involves nonparametric estimation such as smoothing parameter selection and estimation for linear explanatory variables. In this work, several approaches for variable selection are proposed using a fast forward selection algorithm, least angle regression (LARS). The proposed procedures use t-test, all possible regressions comparisons or stepwise selection process with variables selected by LARS. An example based on real data and a simulation study on the performance of the suggested procedures are presented.

• Asia-Pacific Journal of Business
• /
• v.11 no.3
• /
• pp.137-151
• /
• 2020

Purpose - The purpose of this study is to investigate whether financial analysts' cash flow forecasts mitigate the accrual anomaly. In addition, we examine whether the more accurate analysts' cash flow forecasts are the greater the decline of the accrual anomaly. Design/methodology/approach - Data used in the empirical tests are extracted through KIS-VALUE and FN-GUIDE, and the sample consists of firms listed on Korea Stock Exchange for 7 years from 2005 to 2011. We test the hypotheses using multiple regression analysis and we also estimate the regressions with the decile ranks of the explanatory variables to minimize the influence of outliers. Findings - We have failed to capture evidence that the provision of financial analysts' cash flow forecasts itself reduces the accrual anomaly. However, we find the accrual anomaly to be less severe when financial analysts provide more accurate cash flow forecasts. The findings are consistent in the regression models with the decile ranks as well as in the robustness tests that controlled the accruals quality. Research implications or Originality - This study contributes to the expansion of related studies in the Korea by providing empirical evidence partially that the financial analysts' cash flow forecasts mitigate the accrual anomaly.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.2
• /
• pp.373-385
• /
• 2021

The objective of the study is to empirically investigate the impact of bank capital on the lending behavior of Vietnamese commercial banks from 2007 to 2019. Lending behavior is captured by two dimensions, including the quantity (loan growth) and quality (credit risk) of loans. Instead of investigating loan growth and credit risk separately, we combine these two aspects in our study and further develop the interaction term between capital buffers and credit risk to capture the asymmetric impact. We apply the dynamic model (regressed by the generalized method of moments) and the static models (regressed using the fixed effects, random effects, and the pooled regression approach) to perform regressions. The results show that banks with higher capital ratios tend to expand lending more, while the risk of credit portfolios is controlled at lower levels at these banks. Further analysis reveals that credit risk mitigates some aspects of the relationship between bank capital and loan expansion. The patterns remain robust across alternative measures and econometric techniques. The study provides insightful policy implications for bank managers and regulators in the process of upgrading capital resources to ensure the safety and soundness of the banking industry in an emerging country.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.4
• /
• pp.69-81
• /
• 2021

The aim of this paper is to identify the key determinants in the Gulf Cooperation Council (GCC) countries for Foreign Direct Investment (FDI) inflows by using a balanced data panel for the period from 1995 to 2018. This study covers GCC countries in their entirety. The study uses ten explanatory variables, namely, trade ratio, gross domestic product, external balance, fuel exports, gross savings, international tourism, military expenditure, net foreign assets, services value added, and total natural resources. The authors have tried to find the best fit model from the differences methods considered such as OLS, GLS regression with the help of Hausman test, and country by country regressions as additional analysis. The study revealed a significantly positive association between inflation, trade ratio, gross domestic product, gross savings, and net foreign assets with FDI. On the contrary, international tourism was revealed to have a negative association with FDI. The sample of all GCC countries chosen for this study has not been considered widely by any earlier study. Moreover, this study covered many determinants of FDI that add to the previous literature. It is a significant contribution to the current research body and stresses the originality of this paper.

• The Journal of Asian Finance, Economics and Business
• /
• v.9 no.5
• /
• pp.455-463
• /
• 2022

The current study adds to the body of knowledge about the mediation in the causal link between students' perceptions of the utility of eLearning and their learning performance. The data was collected from 500 questionnaires that were delivered to the students at the Vietnam National University of Ho Chi Minh City. Only 422 finished questionnaires were usable for analyses, indicating a responding rate of 84.4%. Multiple regressions were used to investigate causal correlations, whereas Goodman's (1960) techniques were used to investigate mediating relationships. The major findings reveal that both the utility and adoption of eLearning have an impact on students' learning performance, with usefulness being a crucial determinant of eLearning adoption for study. More meaningfully, statistical evidence on the mediation of adopting eLearning for study in the causal linkage from the usefulness of eLearning perceived by students to their learning performance was provided. The relevance of using eLearning for study is stressed in this study, where it is not only one of the key antecedents of their learning performance, but also acts as a mediator between the usefulness of eLearning and learning performance in the research model.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.198-198
• /
• 2022

최근 도시화에 따른 토지 피복 변화와 열섬현상 등의 원인으로 상승하는 도시의 기온이 식물 계절에 미치는 영향에 관한 연구들이 다수 진행되고 있다. 본 연구는 수도권인 서울과 경기도 지역을 대상으로 도시 내 열섬현상으로 인한 기온 상승과 도시 지역 내 식생 생장기간 변화의 관계성을 분석하였다. 식물계절 모니터링에 사용한 개량식생지수(Enhanced Vegetation Index, EVI)는 Google Earth Engine (GEE)에서 제공하는 30 m 해상도의 2000-2021년 NASA-USGS Landsat 위성(TM5, ETM+7, OLI8)의 지표면 반사율(surface reflectance, SR) 자료에서 도출하여 생장기간 산정에 사용하였다. 또한 PRISM (Parameter-elevation Regressions on Independent Slopes Model)을 각 기상관측지점의 일별 지상 기온 자료에 적용하여 30 m 해상도로 생성한 격자형 지표면 온도의 공간적 패턴을 분석하였다. 연구 지역 내 도시화 정도(magnitude)를 도심으로부터의 거리와 환경부 토지피복도 및 인구 밀도를 종합하여 특정하였고, 최종적으로 기후변화 및 도시화 정도와 생장기간 변화의 특징을 분석하였다. 비선형 로지스틱 회귀를 사용하여 EVI 데이터를 종합하여 분석한 결과, 수도권 지역에서 전반적으로 식물계절 개엽일(Start of Season)은 앞당겨지며 낙엽일(End of Season, EOS)은 늦춰져 생장기간(Length of Growing Season, LOS)이 길어짐을 발견하였다.

• Journal of Digital Convergence
• /
• v.17 no.9
• /
• pp.135-145
• /
• 2019

Prolonged recession has caused the youth unemployment rate in Korea to remain at a high level of approximately 10% for years. Recently, the number of unemployed Koreans in their 30s and 40s has shown an upward trend. To expand the government's employment promotion and unemployment benefits from youth-centered policies to diverse age groups, including people in their 30s and 40s, prediction models for different age groups are required. Thus, we aimed to develop unemployment prediction models for specific age groups (30s and 40s) using available unemployment rates provided by Statistics Korea and Google search queries related to them. We first estimated multiple linear regressions (Model 1) using seasonal autoregressive integrated moving average approach with relevant unemployment rates. Then, we introduced Google search queries to obtain improved models (Model 2). For both groups, consequently, Model 2 additionally using web queries outperformed Model 1 during training and predictive periods. This result indicates that a web search query is still significant to improve the unemployment predictive models for Koreans. For practical application, this study needs to be furthered but will contribute to obtaining age-wise unemployment predictions.

• The Korean Journal of Applied Statistics
• /
• v.37 no.3
• /
• pp.339-353
• /
• 2024

In cases where the response variable in proportional data is confined to a limited interval, a regression model based on the assumption of normality can yield inaccurate results due to issues such as asymmetry and heteroscedasticity. In such cases, the beta regression model can be considered as an alternative. This model reparametrizes the beta distribution in terms of mean and precision parameters, assuming that the response variable follows a beta distribution. This allows for easy consideration of heteroscedasticity in the data. In this paper, we therefore aim to analyze proportional data using the beta regression model in two empirical analyses. Specifically, we investigate the relationship between smoking rates and coffee consumption using data from the 6th National Health Survey, and examine the association between regional characteristics in the U.S. and cumulative mortality rates based on COVID-19 data. In each analysis, we apply the ordinary least squares regression model, the beta regression model, and the extended beta regression model to analyze the data and interpret the results with the selected optimal model. The results demonstrate the appropriateness of applying the beta regression model and its extended version in proportional data.

• Water for future
• /
• v.19 no.1
• /
• pp.65-74
• /
• 1986

The purpose of this study was to investigate the applicability of Single Linear Reservoir (SLR) model for runoff computations of small river basins in Korea. In the existing watershed flood routing methods the storage coefficient(K), which is the dominant parameter in the model, has been proposed to be computed in terms of the wqtershed characteristics. However, in the prsent study, the rainfall characteristics in addition to the watershed characteristics were taken into account in the multiple regression analysis for more accurate estimation of storage coefficient. The parameters finally adopted for the regressions were the drainge are, mean stream slope of the watershed, and the duration and total dffective amount of rainfalls. To verify the applicability of SLR model the computed results by SLR model with K determined by the regression equation were compared with the observed gydrographs, and also with those by other runoff computation methods; namely, the Clark method, nakayasu's synthetic unit hydrograph method and Nash model. The results showed that the present zSLR model gave the best results among these methods in the case of small river basins, but for the whatersheds with significant draingage area the Clark method gave the best results. However, it was speculated that the SLR model could also be accurately applied for flood compuatation in large wagersheds provided that the regression for storage coefficients were made with the actual data obtained in the large river basins.

• Korean Journal of Remote Sensing
• /
• v.32 no.4
• /
• pp.383-401
• /
• 2016

In this paper, we described the statistical modeling of crop yields using satellite images, climatic datasets, soil property maps, and fertilizer data for the Midwestern United States during 2001-2012. Satellite images were obtained from the Moderate Resolution Imaging Spectroradiometer (MODIS), and climatic datasets were provided by the Parameter-elevation Regressions on Independent Slopes Model (PRISM) Climate Group. Soil property maps were derived from the Harmonized World Soil Database (HWSD). Our multivariate regression models produced quite good prediction accuracies, with differences of approximately 8-15% from the governmental statistics of corn and soybean yields. The unfavorable conditions of climate and vegetation in 2012 could have resulted in a decrease in yields according to the regression models, but the actual yields were greater than predicted. It can be interpreted that factors other than climate, vegetation, soil, and fertilizer may be involved in the negative biases. Also, we found that soybean yield was more affected by minimum temperature conditions while corn yield was more associated with photosynthetic activities. These two crops can have different potential impacts regarding climate change, and it is important to quantify the degree of the crop sensitivities to climatic variations to help adaptation by humans. Considering the yield decreases during the drought event, we can assume that climatic effect may be stronger than human adaptive capacity. Thus, further studies are demanded particularly by enhancing the data regarding human activities such as tillage, fertilization, irrigation, and comprehensive agricultural technologies.