Global Regression Model Research Articles

Did the COVID-19 Pandemic Disproportionately Affect the Most Socioeconomically Vulnerable Areas of Brazil?

Objective: To analyze the spatial pattern of the incidence of COVID-19 in association with social determinants of health (SDH) in the Northeast Region of Brazil during the first year of the pandemic. Methods: We conducted an ecological analytical study that included notifications made between 27 March 2020 and 27 March 2021. The data analysis used two global regression models: the ordinary least squares (OLS) and spatial lag model and the geographically weighted multiscale regression model (GWMSR). Results: We observed that the Gini index, illiteracy rate, percentages of people living below the poverty line, people in households who were vulnerable to poverty, and dependent elderly people are predictors of a higher incidence of COVID-19 in Northeast Brazil. Conclusions: Results of this study may contribute to generating new hypotheses for studies focusing on the syndemic process and for the formulation of intersectoral public policies targeting the population at greatest vulnerability to minimize the impact of the disease.

Does mobility restriction significantly control infectious disease transmission? Accounting for non-stationarity in the impact of COVID-19 based on Bayesian spatially varying coefficient models.

COVID-19 is the most severe health crisis of the 21st century. COVID-19 presents a threat to almost all countries worldwide. The restriction of human mobility is one of the strategies used to control the transmission of COVID-19. However, it has yet to be determined how effective this restriction is in controlling the rise in COVID-19 cases, particularly in small areas. Using Facebook's mobility data, our study explores the impact of restricting human mobility on COVID-19 cases in several small districts in Jakarta, Indonesia. Our main contribution is showing how the restriction of human mobility data can give important information about how COVID-19 spreads in different small areas. We proposed modifying a global regression model into a local regression model by accounting for the spatial and temporal interdependence of COVID-19 transmission across space and time. We applied Bayesian hierarchical Poisson spatiotemporal models with spatially varying regression coefficients to account for non-stationarity in human mobility. We estimated the regression parameters using an Integrated Nested Laplace Approximation. We found that the local regression model with spatially varying regression coefficients outperforms the global regression model based on DIC, WAIC, MPL, and R2 criteria for model selection. In Jakarta's 44 districts, the impact of human mobility varies significantly. The impacts of human mobility on the log relative risk of COVID-19 range from -4.445 to 2.353. The prevention strategy involving the restriction of human mobility may be beneficial in some districts but ineffective in others. Therefore, a cost-effective strategy had to be adopted.

Geographically weighted regression to measure the role of intra-urban drivers for urban growth modelling in Kathmandu, Central Himalayas.

The present study analyzes spatio-temporal urban growth in Kathmandu Urban Agglomeration (KUA) and its impact on ecological infrastructures between 2000 and 2020. A geographically weighted regression (GWR) approach was used to investigate intra-urban drivers of urban growth between 2000-2010 (epoch 1) and 2010-2020 (epoch 2), and to predict built-up growth for the year 2030. The study makes crucial contributions to the urban growth modelling literature by (a) investigating six different neighborhood sizes (3 × 3 to 13 × 13) for computing proportion of built-up cells and (b) eliminating/selecting covariates using correlation check and globallasso regression. The superiority of GWR model over global regression model has been evaluated using the Akaike information criterion score and the stationarity test. The chronological urban growth analysis of KUA highlights rapid growth in mountainous landscape from 54.90 to 166 km2 during 2000-2020 and is projected to increase to 224.22 km2 during 2000-2030. This has significantly altered the forest-agriculture landscape during 2000-2020 (111.2 km2) and is expected to affect a large segment of ecological (blue-green) infrastructure (138 km2) by 2030. The findings of this study may be used for policy formulation, appropriate land use planning, and sustainable urban development.

Analysis of Urban Ecological Quality Spatial Patterns and Influencing Factors Based on Remote Sensing Ecological Indices and Multi-Scale Geographically Weighted Regression

With the acceleration of urbanization, problems such as urban ecological environment quality have become increasingly prominent. How to scientifically analyze and evaluate the spatial pattern of urban ecological environment changes and influential variables is a prerequisite for achieving green development and ecological priority new in urban planning. Our study was conducted on Pingtan Island, located in Fujian Province, China. First, we selected Landsat 8 OLI images in 2013, 2017, and 2021. Second, we extracted the remote sensing ecological index (RSEI) from these images and created RSEI maps to assess the spatial-temporal variations and spatial autocorrelation of the ecological environment condition in Pingtan Island. Third, the proportion of land-use types, road, and population density were selected as independent variable factors, RSEI as the dependent variable, least squares regression (OLS), geographically weighted regression (GWR), and multi-scale geographically weighted regression (MGWR) were used to establish global and local regression models. According to the regression coefficients of the model and its spatial distribution, the spatial heterogeneity between the ecological environment and the influencing factors was assessed. The results indicated that: (1) the mean value of the RSEI increased from 0.422 to 0.504 during 2013–2021, indicating that the overall ecological environment improved. (2) Based on the global Moran’s I value, the distribution of ecological environment quality was positively correlated. The local Moran’s I cluster map showed that the high-high cluster gradually extended to the northwest high-altitude region. Low-low clustering gradually extended to the more populous areas in the southeast. (3) The Radj2 of the MGWR model was 0.866, which was better than the results of the OLS model and GWR model, indicating that MGWR had obvious advantages in revealing the spatial heterogeneity between the ecological environment and the influencing factors. Importantly, the results indicate that population density, road density, and the proportion of cropland land and impervious surface in land-use types have varying degrees of negative effects on the urban ecological environment, with the impervious surface being more severe, followed by population density, while forest land in land-use types shows significant positive effects.

A retrospective investigation of spatial clusters and determinants of diabetes prevalence: scan statistics and geographically weighted regression modeling approaches.

Diabetes and its complications represent a significant public health burden in the United States. Some communities have disproportionately high risks of the disease. Identification of these disparities is critical for guiding policy and control efforts to reduce/eliminate the inequities and improve population health. Thus, the objectives of this study were to investigate geographic high-prevalence clusters, temporal changes, and predictors of diabetes prevalence in Florida. Behavioral Risk Factor Surveillance System data for 2013 and 2016 were provided by the Florida Department of Health. Tests for equality of proportions were used to identify counties with significant changes in the prevalence of diabetes between 2013 and 2016. The Simes method was used to adjust for multiple comparisons. Significant spatial clusters of counties with high diabetes prevalence were identified using Tango's flexible spatial scan statistic. A global multivariable regression model was fit to identify predictors of diabetes prevalence. A geographically weighted regression model was fit to assess for spatial non-stationarity of the regression coefficients and fit a local model. There was a small but significant increase in the prevalence of diabetes in Florida (10.1% in 2013 to 10.4% in 2016), and statistically significant increases in prevalence occurred in 61% (41/67) of counties in the state. Significant, high-prevalence clusters of diabetes were identified. Counties with a high burden of the condition tended to have high proportions of the population that were non-Hispanic Black, had limited access to healthy foods, were unemployed, physically inactive, and had arthritis. Significant non-stationarity of regression coefficients was observed for the following variables: proportion of the population physically inactive, proportion with limited access to healthy foods, proportion unemployed, and proportion with arthritis. However, density of fitness and recreational facilities had a confounding effect on the association between diabetes prevalence and levels of unemployment, physical inactivity, and arthritis. Inclusion of this variable decreased the strength of these relationships in the global model, and reduced the number of counties with statistically significant associations in the local model. The persistent geographic disparities of diabetes prevalence and temporal increases identified in this study are concerning. There is evidence that the impacts of the determinants on diabetes risk vary by geographical location. This implies that a one-size-fits-all approach to disease control/prevention would be inadequate to curb the problem. Therefore, health programs will need to use evidence-based approaches to guide health programs and resource allocation to reduce disparities and improve population health.

LULC changes to riverine flooding: A case study on the Jamuna River, Bangladesh using the multilayer perceptron model

In riverine nations like Bangladesh, floods are frequent, bringing disaster that impairs people's lives and the national economy. Due to climate change, uncontrolled growth, rapid urbanization, expansion of agriculture plantations, and other factors influence Land-Use-Land-Cover (LULC) changes which can make flooding conditions more unpredictable. The aim of this study is to examine the relationship between changes in LULC and floods in the Jamuna River over a 30-year period from 1990 to 2020 through a quantitative correlational approach. Due to spatial nonlinearity, the relationship between LULC changes and other flood-influencing factors of different areas may vary with flooding. As a result, applying a global regression model can produce biased results in certain locations. We employed the multilayer perceptron neural network and Geographically Weighted Regression (GWR) method to solve this issue. The GWR method applies local regression based on carefully chosen criteria to handle spatial variability. A multilayer perceptron neural network was used to determine the potential for riverine flooding. The study's findings revealed that LULC changes in the area far from the river had a significant impact on changes in riverine flooding, as shown by the fact that 29.71% of those locations had a Pearson coefficient greater than 0.75. In contrast, LULC changes near the river did not strongly correlate with changes in riverine flood potential because 19.83% of those locations had a very low Pearson coefficient of less than 0.75.

Spatial Analysis of Nigeria’s Presidential Election Based on Geographically Weighted Regression

Geographically weighted regression (GWR) is a linear regression technique used to fit a regression equation to every observation in a dataset. In this study, both the global regression (multiple linear regression) and the GWR were calibrated for the 2019 Nigeria presidential election dataset, and diagnostics of each model were computed and compared. Experiments and analyses in the study were implemented in the R-environment, R-4.1.2. The GWR model outperforms the global regression model with an R^2 value of 0.776 exceeding that of the global regression of 0.513. The superiority of the GWR model is also confirmed by its much smaller RSS and AICc values (173.362 and 1372.8555 respectively), compared to those of the global regression (377.103 and 1662.316 respectively). The GWR model better fits the election dataset; it explains spatial variations in the dependent variable better than the global regression model does.

Towards Convergence in Federated Learning via Non-IID Analysis in a Distributed Solar Energy Grid

Federated Learning (FL) is an effective framework for a distributed system that constructs a powerful global deep learning model, which diminishes the local bias and accommodates the successful aggregation of locally trained models with heterogeneous datasets. However, when local datasets have the non-IID attribute, the optimization metric tends to diverge or show unstable convergence in the trajectory space. This paper delves into building a global model for the distributed Smart Grid environment, with regionally cumulated three solar energy datasets from January 2017 to August 2021 in a decentralized power grid in South Korea via FL. This distributed energy network involves local properties and physical distance between the regions, which raises a fundamental question of “Will time-serially curated non-IID local features be effective in constructing a global regression model?”. This paper probes this question by leveraging FL and conducts the theoretically viable non-IID case-by-case convergence analysis, providing the interpretation of the embedded temporal non-IID features and application on real-world data. Moreover, most of the FL studies predetermine the global update period, which lacks applicability when adapting FL in actual practice. As FL is a cumulative-basis structure, the update term is a crucial factor that needs to be carefully selected. This paper articulates this problem and explores the effective update period via multiple experiments on the 4.5 years of solar energy dataset, and to the best of my knowledge, this is the first literature that presents the optimal update period in the FL regression in an energy domain.

Lockdown lifted: measuring spatial resilience from London’s public transport demand recovery

ABSTRACT The disruptive effects of the COVID-19 pandemic has rapidly shifted how individuals navigate in cities. Governments are concerned that travel behavior will shift toward a car-driven and homeworking future, shifting demand away from public transport use. These concerns place the recovery of public transport in a possible crisis. A resilience perspective may aid the discussion around recovery – particularly one that deviates from pre-pandemic behavior. This paper presents an empirical study of London’s public transport demand and introduces a perspective of spatial resilience to the existing body of research on post-pandemic public transport demand. This study defines spatial resilience as the rate of recovery in public transport demand within census boundaries over a period after lockdown restrictions were lifted. The relationship between spatial resilience and urban socioeconomic factors was investigated by a global spatial regression model and a localized perspective through Geographically Weighted Regression (GWR) model. In this case study of London, the analysis focuses on the period after the first COVID-19 lockdown restrictions were lifted (June 2020) and before the new restrictions in mid-September 2020. The analysis shows that outer London generally recovered faster than inner London. Factors of income, car ownership and density of public transport infrastructure were found to have the greatest influence on spatial patterns in resilience. Furthermore, influential relationships vary locally, inviting future research to examine the drivers of this spatial heterogeneity. Thus, this research recommends transport policymakers capture the influences of homeworking, ensure funding for a minimum level of service, and advocate for a polycentric recovery post-pandemic.

Unpacking the inter- and intra-urban differences of the association between health and exposure to heat and air quality in Australia using global and local machine learning models

Environmental stressors including high temperature and air pollution cause health problems. However, understanding how the combined exposure to heat and air pollution affects both physical and mental health remains insufficient due to the complexity of such effects mingling with human society, urban and natural environments. Our study roots in the Social Ecological Theory and employs a tri-environmental conceptual framework (i.e., across social, built and natural environment) to examine how the combined exposure to heat and air pollution affect self-reported physical and mental health via, for the first time, the fine-grained nationwide investigation in Australia and highlight how such effects vary across inter- and intra-urban areas. We conducted an ecological study to explore the importance of heat and air quality to physical and mental health by considering 48 tri-environmental confounders through the global and local random forest regression models, as advanced machine learning methods with the advantage of revealing the spatial heterogeneity of variables. Our key findings are threefold. First, the social and built environmental factors are important to physical and mental health in both urban and rural areas, and even more important than exposure to heat and air pollution. Second, the relationship between temperature and air quality and health follows a V-shape, reflecting people's different adaptation and tolerance to temperature and air quality. Third, the important roles that heat and air pollution play in physical and mental health are most obvious in the inner-city and near inner-city areas of the major capital cities, as well as in the industrial zones in peri-urban regions and in Darwin city with a low-latitude. We draw several policy implications to minimise the inter- and intra-urban differences in healthcare access and service distribution to populations with different sensitivity to heat and air quality across urban and rural areas. Our conceptual framework can also be applied to examine the relationship between other environmental problems and health outcomes in the era of a warming climate.

Enhanced regression model using cluster based sampling techniques

This paper aims to develop the methodology for enhancing the regression models using Cluster based sampling techniques (CST) to achieve high predictive accuracy and can also be used to handle large datasets. Hard clustering (KMeans Clustering) or Soft clustering (Fuzzy C-Means) to generate samples called clusters, which in turn is used to generate the Local Regression Models (LRM) for the given dataset. These LRMs are used to create a Global Regression Model. This methodology is known as Enhanced Regression Model (ERM). The performance of the proposed approach is tested with 5 different datasets. The experimental results revealed that the proposed methodology yielded better predictive accuracy than the non-hybrid MLR model; also, fuzzy C-Means performs better than the KMeans clustering algorithm for sample selection. Thus, ERM has potential to handle data with uncertainty and complex pattern and produced a high prediction accuracy rate.

An analysis of the impact of China's macroeconomic performance on its trade partners: Evidence based on the GVAR model.

Economic strategies and planning are critical to a country's growth and development. China, like many other countries, is seeking the most cost-effective trade deals. Using the Global Vector Auto Regression (GVAR) model, this study examined the impact of a shock to China's macroeconomic factors on trading economies. The major findings reveal that there is no co-movement between the shock in Chinese gross domestic product (GDP) and German macroeconomic indicators; however, the shock has a positive and substantial influence on Japan's GDP and Unites States (US)' exchange rate. It is also worth noting that a shock to Chinese trade volume is more susceptible and more disturbing than a shock to US trade volume since it reduces trade volume and causes the Ren Min Bi (RMB) to devalue permanently. Furthermore, the analysis shows that Chinese stock prices have a major influence on German economy since China's GDP, trade volume, and currency appreciate over time when its stock price rises. Finally, the exchange rate shock is beneficial to Germany as it boosts GDP and trade volume but has a negative influence on US stock prices. The current study is, therefore, expected to be a suitable beginning point for the governments and policymakers of trading partners to design an effective trade policy to minimize the impact on major economic variables.

Analysis of the energy justice in natural gas distribution with Multiscale Geographically Weighted Regression (MGWR)

Energy justice is violated when particular customers and locations are excluded from a variety of urban energy service distribution. This study explores energy justice in terms of natural gas distribution by providing empirical evidence from 356 neighborhoods of Izmir Metropolitan Area (IMA). The aim is to reveal driving factors of natural gas investment and the spatial reflections of the relationships between investment, and socio-economic and physical characteristics. A global regression model, OLS, and two local spatial regression models, GWR and MGWR, are conducted. Population, income, employment and disadvantaged areas are the significant determinants of natural gas investments. Due to the presence of spatial autocorrelation in OLS residuals, GWR and MGWR are utilized to account for spatial variation in the response variable. Local models are superior to the global model according to AICc values, which are 607.3, 586.7, and 558.5, in OLS, GWR, and MGWR, respectively. MGWR further improves the overall fit with higher R-sq and lower AICc values. The local R-sq values indicate at least 70% variability is explained in 85% of the study area in MGWR, and in 73% of IMA in GWR. Parameters are slightly overestimated in GWR at the mean level. None of the local models are subject to multicollinearity according to local condition numbers, but local variance decomposition proportions indicate the effects of multicollinearity in some observations. Spatial modeling of investments helps to demonstrate local variations of energy injustice and to develop site-specific policies. Population and employment are related to potential customers, which lead to higher investments. Income depends on purchasing power, and there are economic barriers that need to be regulated through subsidies and incentives for the low-income households. Awareness raising policies can also be developed to better inform households about energy alternatives. Disadvantaged areas, either declared as urban transformation areas or currently under urban transformation, lack the natural gas service in general, while the investments can be considered in those areas along with the new development plans.

Temporal heterogeneous effects of land-use on dockless bike-sharing usage under transit-oriented development context: The case of Beijing

The transit-oriented development (TOD) is an effective planning strategy for achieving the Sustainable Development Goals (SDGs) in transportation by incentivizing active transport. As an active transport with high flexibility and affordability, the use of dockless bike-sharing (DBS) services was affected by many identified factors. However, few studies have examined this effect from a temporally heterogeneous perspective. Here, this study aims to test if there are heterogeneous effects of station-level land-use on the use of DBS across time and to explore how and to what extent station-level land-use affects the use of DBS dynamically. Taking Beijing as a case study, this study developed the Global Linear Regression models and the Time-Varying Coefficients panel data models to estimate the heterogeneity. The results prove the existence of heterogeneity on both working days and non-working days. The daily DBS trips were significantly correlated to the density, diversity, and most types of land-use; the effect of density maintained a high level and varies with hours, and the effect of diversity showed an insignificant effect on hourly DBS trips. Besides, public management and service facilities were critical in influencing DBS usage during the daily off-peak hours, while residences always significantly and positively correlated to the use of DBS before morning peak hours and after evening peak hours. Further, the study suggests an active transfer of DBS facilities in the businesses and commercial areas to surrounding areas during non-working days. The findings guide the improvement of the service efficiency of DBS systems, and integrate DBS management strategies into TOD practice toward SDGs.

Deconstructing the driving factors of land development intensity from multi-scale in differentiated functional zones

Land development intensity (LDI) is an important indicator of how much human exploitation of land resources. Against the background of rapid urbanization and industrialization, in order to curb the over-occupation of agricultural and ecological space by urbanized space, China has proposed the Major Functional Zoning Planning (MFZP) as a new spatial governance model, which attempts to implement differentiated LDI control according to the functional positioning of different regions. To observe the spatio-temporal evolution and drivers of LDI in the first five years since the implementation of the MFZP, we chose the Yangtze River Delta, the most urbanized region in China, as a case area. The multi-scale distribution pattern of LDI was analyzed by combining macro and micro scales, and a new spatial measurement method integrating global and local regression models was developed to quantitatively deconstruct the natural-human drivers of LDI in different functional zones. Results demonstrate that LDI decreases in a gradient of the urbanized zone (UZ) > main agricultural production zone (MAPZ) > key ecological function zone (KEFZ). In the UZ, LDI is influenced by natural-human multi factors, e.g., terrain conditions (SLP), proportion of cultivated land area (PCL), proportion of ecologically important area (EID), population urbanization rate (PUR), GDP per capita (PGDP), fixed asset investment size per land (FAI) and fiscal expenditure as a percentage of GDP (FD). The LDI in the MAPZ is mainly affected by the facilitating role of PCL, EID, FAI, and the prominent role of FD, while that in the KEFZ is mainly inhibited by SLP, EID, and driven by the PGDP. The diverse drivers of LDI in different functional zones remind us to implement differentiated spatial control according to functional positioning and to adopt refined policy tools of zoning and classification to ensure that land resources within each type of functional zone can be used sustainably.

Improved estimation of herbaceous crop aboveground biomass using UAV-derived crop height combined with vegetation indices

Vegetation indices are used in precision agriculture to estimate crop aboveground biomass (AGB) and, in turn, to quantify crop needs. However, crop species and development stage affect vegetation indices limiting the setup of generalized models for AGB estimation. Some approaches to overcome this issue have combined vegetation indices and structural crop properties such as crop height. However, only a few studies have considered different herbaceous crops like forages and cover crops. A 2-year field experiment was carried out on five winter cover crops with different habits at a high cover fraction (on average 93%) to study if combining vegetation indices, crop height and the fraction of soil covered by the crop could improve AGB estimation. Seven vegetation indices, crop height and cover fraction were derived from UAV-multispectral images. Species-specific and global (including all species) regression models were built and tested through cross-validation (CV). Green-based indices were the best estimators of AGB (RCV2 = 0.56–0.93, normalized root mean square error in CV nRMSECV = 26–38%) of the five species, separately. A global linear model using crop height alone, provided good results (RCV2 = 0.57, nRMSECV = 42%). Also, stepwise multiple regression was used to get a global model with crop height and five vegetation indices (RCV2 = 0.75, nRMSECV = 31%). Finally, a model was proposed where AGB was estimated by a vegetation index until plants covered 97% of soil or its height was shorter than 125 mm and by crop height for vegetation taller than 125 mm. The promising results (RCV2 = 0.65, nRMSECV = 36%) suggested the possibility of increasing AGB estimation by considering both vegetation indices and structural crop properties.

A spatial regression modeling framework for examining relationships between the built environment and pedestrian crash occurrences at macroscopic level: A study in a developing country context

Researchers have been trying to identify the contributory factors behind pedestrian crash occurrences through studies at both microscopic and macroscopic levels. However, built environment-related factors have primarily been examined in developed countries, resulting in a limited understanding of the phenomenon in the context of developing countries. Methodologically, these studies mostly used global regression models, which failed to incorporate spatial autocorrelation and spatial heterogeneity. Additionally, some of these studies applied spatial regression models randomly without following a comprehensive logical framework behind their selections. Our study aimed to develop a comprehensive spatial regression modeling framework to examine the relationships between pedestrian crash occurrences and the built environment at the macroscopic level in a megacity, Dhaka, the capital of a developing country: Bangladesh. Using secondary pedestrian crash data, the study applied one global non-spatial model, two global spatial regression models, and two local spatial regression models following a comprehensive spatial regression modeling framework. The factors which significantly contributed to pedestrian crash occurrences in Dhaka were employed person density, mixed and recreational land use density, primary road density, major intersection density, and share of non-motorized modes. Except for the last factor, all the other ones were positively related to pedestrian crash density. Among the five models used in this study, the multiscale geographically weighted regression (MGWR) performed the best as it calibrated each local relationship with a distant spatial scale parameter. The findings and recommendations presented in this study would be useful for reducing pedestrian crashes and choosing the appropriate modeling technique for crash analysis.

Spatiotemporal clusters and the socioeconomic determinants of COVID-19 in Toronto neighbourhoods, Canada

The aim of this study is to identify spatiotemporal clusters and the socioeconomic drivers of COVID-19 in Toronto. Geographical, epidemiological, and socioeconomic data from the 140 neighbourhoods in Toronto were used in this study. We used local and global Moran's I, and space-time scan statistic to identify spatial and spatiotemporal clusters of COVID-19. We also used global (spatial regression models), and local geographically weighted regression (GWR) and Multiscale Geographically weighted regression (MGWR) models to identify the globally and locally varying socioeconomic drivers of COVID-19. The global regression model identified a lower percentage of educated people and a higher percentage of immigrants in the neighbourhoods as significant predictors of COVID-19. MGWR shows the best fit model to explain the variables affecting COVID-19. The findings imply that a single intervention package for the entire area would not be an effective strategy for controlling COVID-19; a locally adaptable intervention package would be beneficial.

Exploring regional and sociodemographic disparities associated with unenrollment for the disease management program for type 2 Diabetes Mellitus using Bayesian spatial modelling

BackgroundThe disease management program (DMP) for type 2 Diabetes Mellitus (T2DM) is the largest DMP in Germany. Our goal was to analyze regional differences in unenrollment rates, suggest areas for intervention and provide background information, which population groups in which locations are currently not enrolled in the DMP for T2DM.MethodsIn this study, we used data of the 1.7 mil. insurants of the AOK Nordost health insurance. For the visualization of enrollment potential, we used the Besag-York-Mollie model (BYM). The spatial scan statistic (SaTScan) was used to detect areas of unusually high rates of unenrolled diabetics to prioritize areas for intervention. To explore sociodemographic associations, we used Bayesian spatial global regression models. A Spatially varying coefficient model (SVC) revealed in how far the detected associations vary over space.ResultsThe proportion of diabetics currently not enrolled in the DMP T2DM was 36.8% in 2019 and varied within northeastern Germany. Local clusters were detected mainly in Mecklenburg-West-Pomerania and Berlin. The main sociodemographic variables associated with unenrollment were female sex, younger age, being unemployed, foreign citizenship, small household size and the proportion of persons commuting to work outside their residential municipality. The SVC model revealed important spatially varying effects for some but not all associations.ConclusionLower socioeconomic status and foreign citizenship had an ubiquitous effect on not being enrolled. The DMP T2DM therefore does currently not reach those population groups, which have a higher risk for secondary diseases and possible avoidable hospitalizations. Logically, future interventions should focus on these groups. Our methodology clearly suggests areas for intervention and points out, which population group in which locations should be specifically approached.

Agricultural Grain Markets in the COVID-19 Crisis, Insights from a GVAR Model

The objective of this paper is to combine cross-commodity and spatial price transmission analysis to study the dynamics of the global cereal feed market during the COVID-19 pandemic. After reviewing the nascent literature on the impact of COVID-19 on agricultural markets, we discuss the different impact channels on prices. Then, we provide stylized market reactions of three relevant feed markets, wheat, barley, and maize, to a set of simulated possible future shocks on oil prices, stock-to-use ratios, and export restrictions. These three shocks are useful to assess what could be the consequences of policy responses to COVID-19 (export restrictions) or the disruptions due to the virus (stock-to-use reductions), in a context of lower oil prices. To generate these market reactions, we use a Global Vector Auto Regression (GVAR) model where each market is modelled independently, and connected through trade-based composite variables. We expand the work on the global wheat market by introducing maize and barley. The results of the empirical analysis indicate that the fall in the oil price may have contributed to the stability of the world grain market in early 2020, despite fears of supply chain disruption. We also note that export restrictions could significantly increase global prices, and that such restrictions could affect more than the targeted commodity, through significant cross-commodity price linkages.