scholarly journals Review on Geographically Weighted Regression (GWR) approach in spatial analysis

2020 ◽  
Vol 16 (2) ◽  
pp. 173-177
Author(s):  
Ayuna Sulekan ◽  
Shariffah Suhaila Syed Jamaludin
Keyword(s):  
Spatial Analysis ◽  
Geographically Weighted Regression ◽  
Prediction Models ◽  
Geographical Location ◽  
Spatial Relationship ◽  
Spatial Prediction ◽  
Multiple Regression Model ◽  
Weighted Regression ◽  
Physical Factors ◽  
The Relationship

 In spatial analysis, it is important to identify the nature of the relationship that exists between variables. Normally, it is done by estimating parameters with observations which taken from different spatial units that across a study area where parameters are assumed to be constant across space. However, this is not so as the spatial non-stationarity is a condition in which a simple model cannot explain the relationship between some sets of variables. The nature of the model must alter over space to reflect the structure within the data. Non-stationarity means that the relationship between variables under study varies from one location to another depending on physical factors of the environment that are spatially autocorrelated. Geographically Weighted Regression (GWR) is a technique in which it applied to capture the variation by calibrating a multiple regression model, which allows different relationships to exist at different points in space. A robust algorithm has been successfully used in spatial analysis. GWR can theoretically integrate geographical location, altitude, and other factors for spatial analysis estimations, and reflects the non-stationary spatial relationship between these variables. The main goal of this study is to review the potential of the GWR in modelling the spatial relationship between variables either dependent or independent and its used as the spatial prediction models. Based on the application of GWR such as house property indicates that GWR is the best model in estimating the parameters. Hence, from the GWR model, the significance of the variation can also be tested

Government failures and non-performing loans in European countries: a spatial approach

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Ferdinando Ofria ◽  
Massimo Mucciardi
Keyword(s):  
Public Debt ◽  
Geographically Weighted Regression ◽  
European Countries ◽  
Weighted Regression ◽  
Second Step ◽  
Ols Regression ◽  
Content Type ◽  
The Impact ◽  
The Relationship ◽  
The Eu

PurposeThe purpose is to analyze the spatially varying impacts of corruption and public debt as % of GDP (proxies of government failures) on non-performing loans (NPLs) in European countries; comparing two periods: one prior to the crisis of 2007 and another one after that. The authors first modeled the NPLs with an ordinary lest square (OLS) regression and found clear evidence of spatial instability in the distribution of the residuals. As a second step, the authors utilized the geographically weighted regression (GWR) to explore regional variations in the relationship between NPLs and the proxies of “Government failures”.Design/methodology/approachThe authors first modeled the NPL with an OLS regression and found clear evidence of spatial instability in the distribution of the residuals. As a second step, the author utilized the Geographically Weighted Regression (GWR) (Fotheringham et al., 2002) to explore regional variations in the relationship between NPLs and proxies of “Government failures” (corruption and public debt as % of GDP).FindingsThe results confirm that corruption and public debt as % of GDP, after the crisis of 2007, have affected significantly on NPLs of the EU countries and the following countries neighboring the EU: Switzerland, Iceland, Norway, Montenegro, and Turkey.Originality/valueIn a spatial prospective, unprecedented in the literature, this research focused on the impact of corruption and public debt as % of GDP on NPLs in European countries. The positive correlation, as expected, between public debt and NPLs highlights that fiscal problems in Eurozone countries have led to an important rise of problem loans. The impact of institutional corruption on NPLs reports that the higher the corruption, the higher is the level of NPLs.

Analyzing Resilience in Local Labor Market Areas: A Spatial Analysis for the Case of Italy

2019 ◽  
Vol 65 (3) ◽  
pp. 189-208
Author(s):  
Barbara Martini ◽  
Marco Platania
Keyword(s):  
Labor Market ◽  
Spatial Analysis ◽  
Spatial Data ◽  
Spatial Relationship ◽  
Spatial Data Analysis ◽  
Market Area ◽  
Observation Unit ◽  
Local Labor Market ◽  
Market Areas ◽  
The Relationship

Abstract The aim of the paper is to analyse if and in which way specialization, geographical localization and spill-over effects affect resilience. The research is carried out using LLMAs (Local Labor Market Areas) as observational unit and spatial data analysis techniques (Anselin 1999, LeSage & Pace, 2009) in Italy. Resilience literature focalized its attention on regions. Despite this, there is no general agreement regarding the most appropriate observation unit. Our aim is not only to investigate the relationship between specialization and resilience at smaller scale using the LLMAs as observation unit but also to explore the spatial relationship among them. Results highlight a strong spatial correlation among LLMAs. As consequence resilience is not only influenced by specialization but also by geographical localization through spill-over effects. JEL Classifications: R10, R12, C23, C33 Spatial analysis; Resilience; Labor Market Area; Italy

scholarly journals Estimation of Forest Above-Ground Biomass by Geographically Weighted Regression and Machine Learning with Sentinel Imagery

Forests ◽  
2018 ◽  
Vol 9 (10) ◽  
pp. 582 ◽  
Author(s):  
Lin Chen ◽  
Chunying Ren ◽  
Bai Zhang ◽  
Zongming Wang ◽  
Yanbiao Xi
Keyword(s):  
Machine Learning ◽  
Geographically Weighted Regression ◽  
Prediction Models ◽  
Forest Degradation ◽  
Weighted Regression ◽  
Changbai Mountains ◽  
Support Vector ◽  
Above Ground Biomass ◽  
Ground Biomass ◽  
Texture Characteristics

Accurate forest above-ground biomass (AGB) is crucial for sustaining forest management and mitigating climate change to support REDD+ (reducing emissions from deforestation and forest degradation, plus the sustainable management of forests, and the conservation and enhancement of forest carbon stocks) processes. Recently launched Sentinel imagery offers a new opportunity for forest AGB mapping and monitoring. In this study, texture characteristics and backscatter coefficients of Sentinel-1, in addition to multispectral bands, vegetation indices, and biophysical variables of Sentinal-2, based on 56 measured AGB samples in the center of the Changbai Mountains, China, were used to develop biomass prediction models through geographically weighted regression (GWR) and machine learning (ML) algorithms, such as the artificial neural network (ANN), support vector machine for regression (SVR), and random forest (RF). The results showed that texture characteristics and vegetation biophysical variables were the most important predictors. SVR was the best method for predicting and mapping the patterns of AGB in the study site with limited samples, whose mean error, mean absolute error, root mean square error, and correlation coefficient were 4 × 10−3, 0.07, 0.08 Mg·ha−1, and 1, respectively. Predicted values of AGB from four models ranged from 11.80 to 324.12 Mg·ha−1, and those for broadleaved deciduous forests were the most accurate, while those for AGB above 160 Mg·ha−1 were the least accurate. The study demonstrated encouraging results in forest AGB mapping of the normal vegetated area using the freely accessible and high-resolution Sentinel imagery, based on ML techniques.

Spatial modelling of soil organic carbon stocks with combined principal component analysis and geographically weighted regression

2018 ◽  
Vol 156 (6) ◽  
pp. 774-784 ◽  
Author(s):  
Long Guo ◽  
Mei Luo ◽  
Chengsi Zhangyang ◽  
Chen Zeng ◽  
Shanqin Wang ◽  
...  
Keyword(s):  
Principal Component Analysis ◽  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Geographically Weighted Regression ◽  
Environmental Variables ◽  
Prediction Models ◽  
Principal Component ◽  
Weighted Regression ◽  
Auxiliary Variables ◽  
Soc Stocks

AbstractWith the development of remote sensing and geostatistical technology, complex environmental variables are increasingly easily quantified and applied in modelling soil organic carbon (SOC). However, this emphasizes data redundancy and multicollinearity problems adding to the difficulty in selecting dominant influential auxiliary variables and uncertainty in estimating SOC stocks. The current paper considers the spatial characteristics of SOC density (SOCD) to construct prediction models of SOCD on the basis of reducing the data dimensionality and complexity using the principal component analysis (PCA) method. A total of 260 topsoil samples were collected from Chahe town, China. Eight environmental variables (elevation, aspect, slope, normalized difference vegetation index, normalized difference moisture index, nearest distance to construction area and road, and land use degree comprehensive index) were pre-analysed by PCA and then extracted as the main principal component variables to construct prediction models. Two geostatistical approaches (ordinary kriging and ordinary co-kriging) and two regression approaches (ordinary least squares and geographically weighted regression (GWR)) were used to estimate SOCD. Results showed that PCA played an important role in reducing the redundancy and multicollinearity of the auxiliary variables and GWR achieved the highest prediction accuracy in these four models. GWR considered not only the spatial characteristics of SOCD but also the related valuable information of the auxiliary attributes. In summary, PCA-GWR is a promising spatial method used here to predict SOC stocks.

Sign in / Sign up

Export Citation Format

Share Document