• Journal of Korean Society for Geospatial Information Science
• /
• v.21 no.4
• /
• pp.73-81
• /
• 2013

Ordinary least squares (OLS) regression is the primary statistical method in previous studies for vegetation distribution patterns in relation to landform. However, this global regression lacks the ability to uncover some local-specific relationships and spatial autocorrelation in model residuals. This study employed geographically weighted regression (GWR) to examine the spatially varying relationships between NDVI (Normalized Difference Vegetation Index) patterns and changing trends of landform (elevation, slope) and solar intensity (insolation and duration of sunshine) in Mt Geum-gang of North-Korea. Results denoted that GWR was more powerful than OLS in interpreting relationships between NDVI patterns and landform/solar intensity, since GWR was characterized by higher adjusted R2, and reduced spatial autocorrelations in model residuals. Unlike OLS regression, GWR allowed the coefficients of explanatory variables to differ by locality by giving relatively more weight to NDVI patterns which are affected by local landform and solar factors. The strength of the regression relationships in the GWR increased significantly, by showing regression coefficient of higher than 70% (0.744) in the southern ridge of the experimental area. It is anticipated that this research output will serve to increase the scientific and objective vegetation monitoring in relation to landform and solar intensity by overcoming serious constraints suffered from the past non-GWR-based approach.

• Journal of the Korean Data and Information Science Society
• /
• v.14 no.2
• /
• pp.355-366
• /
• 2003

A unified procedure for principal component regression (PCR), partial least squares (PLS) and ordinary least squares (OLS) is proposed. The process gives solutions for PCR, PLS and OLS in a unified and non-iterative way. This enables us to see the interrelationships among the three regression coefficient vectors, and it is seen that the so-called E-matrix in the solution expression plays the key role in differentiating the methods. In addition to setting out the procedure, the paper also supplies a robust numerical algorithm for its implementation, which is used to show how the procedure performs on a real world data set.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.32 no.4_1
• /
• pp.343-351
• /
• 2014

The correlation between regional Walkability Index and their physical socio-economic characteristics has evaluated by the spatial statistical analysis to understand the urban pedestrian environments, where has been emerging the significance, recently. Following to the study, the Walkability Indexes were calculated quantitatively from two administrative districts of Busan and measured Global Local spatial autocorrelation indices. Additionally, the Geographically Weighted Regression model was applied to define the correlation between Walkability Indexes and urban environmental variables. The spatial autocorrelation values and clusters on the Walkability Indexes were derived in statistically significant level. Furthermore, the Geographically Weighted Regression model has been derived more improved inference than the OLS regression model, so as the influence of local level pedestrian environment was identified. The results of this study suggest that the spatial statistical approach can be effective on quantitative assessing the pedestrian environment and navigating their associated factors.

• Health Policy and Management
• /
• v.26 no.4
• /
• pp.271-278
• /
• 2016

Background: This study purposed to analyze the relationship between regional obesity rates and regional variables. Methods: Data was collected from the Korean Statistical Information Service (KOSIS) and Community Health Survey in 2012. The units of analysis were administrative districts such as city, county, and district. The dependent variable was the age-sex adjusted regional obesity rates. The independent variables were selected to represent four aspects of regions: health behaviour factor, psychological factor, socio-economic factor, and physical environment factor. Along with the traditional ordinary least square (OLS) regression analysis model, this study applied geographically weighted regression (GWR) analysis to calculate the regression coefficients for each region. Results: The OLS results showed that there were significant differences in regional obesity rates in high-risk drinking, walking, depression, and financial independence. The GWR results showed that the size of regression coefficients in independent variables was differed by regions. Conclusion: Our results can help in providing useful information for health policy makers. Regional characteristics should be considered when allocating health resources and developing health-related programs.

• Journal of the Korean Statistical Society
• /
• v.23 no.1
• /
• pp.33-38
• /
• 1994

The OLS-estimator of the distribance variance in the linear regression model is shown to be asymptotically unbiased when the disturbances are MA(1)-process or particular s-th autocorrelated AR(s)-process.

• The Korean Journal of Health Service Management
• /
• v.8 no.2
• /
• pp.11-22
• /
• 2014

This study purposed to analyze the regional variation of the local-out rates of inpatient services. Multiple data sources collected from National Health Insurance Corporation and statistics Korea were merged to produce the analysis data set. The unit of analysis in this study was city, Gun, Gu, and all of them were included in analysis. The dependent variable measured the local-out rate of inpatient cost in study regions. Local environments were measured by variables in three dimensions: provider factors, socio-demographic factors, and health status. Along with the traditional ordinary least square (OLS) based regression model, geographically weighted regression (GWR) model were applied to test their effects. SPSS v21 and ArcMap v10.2 were applied for the statistical analysis. Results from OLS regression showed that most variables had significant relationships with the local-out rate of inpatient services. However, some variables had shown diverse directions in regression coefficients depending on regions in GWR. This implied that the study variables might not have consistent effects and they may varied depending the locations.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.29 no.3
• /
• pp.111-116
• /
• 2021

This study aims to identify the representative factors affecting the air trade between the two countries over the past 20 years, targeting China, Korea's largest trading partner for air transport. In the analysis, the two countries' GDP, GDP per capita, and tariff rates, as well as exchange rates, international oil prices, and FTAs were used as variables. For the analysis method, OLS multiple regression analysis was performed, and each was analyzed by dividing the export amount, import amount, and trade amount. As a result of the analysis, China's GDP and Korea's GDP per capita showed a positive (+) direction, an increase in the exchange rate resulted in an increase in the amount of trade, and an increase in the tariff rate resulted in a decrease in the amount of trade. Whether the FTA was concluded or not acted as a factor in increasing the amount of trade between the two countries.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.29 no.2
• /
• pp.106-110
• /
• 2021

In this study, the main factors affecting the number of passengers and cargo volume transported by air between Korea, China and Japan over the past 20 years are to be identified. For the analysis, data from three countries' GDP and per capita as well as exchange rates and international oil prices were used, and OLS multiple regression analysis and fixed effect analysis were performed. As a result of the analysis, both the number of passengers and cargo volume transported by air showed a negative (-) direction for GDP, which represents the country's economic power, and a positive (+) direction, for per capita GDP, which represents income level. And the increase in the exchange rate between China and Japan acted in a positive (+) direction on the increase in the number of passengers, and the effect of oil prices was found to be limited.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.11
• /
• pp.219-229
• /
• 2020

The study investigates the factors affecting the profitability of listed commercial banks in Vietnam. Survey data for this research were collected from 10 Vietnamese listed commercial banks for the period from 2008 to 2018. In the study, we have built a model of econometric regression with the dependent variable being listed commercial banks' profitability results measured through ROA. The research methods used include descriptive statistics, IV regression and OLS regression analysis, and the authors carried out the model verification with Stata 14 software. The results showed that operating efficiency, loans size, retail loans ratio, state ownership, inflation rate, and GDP growth are factors that have a positive impact on profitability On the other hand, variables such as capital size, credit risk, liquidity risk, bank size, and revenue diversification are statistically insignificant; hence, these variables are not statistically adequate to indicate the influence of those independent variables to banks' profitability. The findings of this study suggest that the quality of assets should be considered in the context that bad debt risks come from lending heavily to the real estate sector. Meeting Basel II's capital compliance requirements is relatively difficult for small listed commercial banks compared to bigger listed commercial banks in Vietnam.

• Communications for Statistical Applications and Methods
• /
• v.18 no.6
• /
• pp.733-739
• /
• 2011

The linear absolute shrinkage and selection operator(Lasso) method improves the low prediction accuracy and poor interpretation of the ordinary least squares(OLS) estimate through the use of $L_1$ regularization on the regression coefficients. However, the Lasso is not robust to outliers, because the Lasso method minimizes the sum of squared residual errors. Even though the least absolute deviation(LAD) estimator is an alternative to the OLS estimate, it is sensitive to leverage points. We propose a robust Lasso estimator that is not sensitive to outliers, heavy-tailed errors or leverage points.