Browsing by Subject "Spatial econometrics"

Now showing 1 - 4 of 4

Modelling and diagnostics of spatially autocorrelated counts
(2022) Jung, Robert C.; Glaser, Stephanie
This paper proposes a new spatial lag regression model which addresses global spatial autocorrelation arising from cross-sectional dependence between counts. Our approach offers an intuitive interpretation of the spatial correlation parameter as a measurement of the impact of neighbouring observations on the conditional expectation of the counts. It allows for flexible likelihood-based inference based on different distributional assumptions using standard numerical procedures. In addition, we advocate the use of data-coherent diagnostic tools in spatial count regression models. The application revisits a data set on the location choice of single unit start-up firms in the manufacturing industry in the US.
Modelling of spatial effects in count data
(2017) Glaser, Stephanie; Jung, Robert
In this thesis, spatial structures in discrete valued count observations are modelled. More precisely, a global spatial autocorrelation parameter is estimated in the framework of a nonlinear count data regression model. For this purpose, cross-sectional and panel count data models are developed which incorporate spatial autocorrelation and allow for additional explanatory variables. The proposed models include the so-called "Spatial linear feedback model" for cross-sectional data as well as for panel data including fixed effects, which is estimated using maximum likelihood estimation. Additionally, two approaches for a distribution-free panel estimation using GMM are presented. The models are applied to a cross-sectional U.S. start-up firm births data set and a panel data set with crime counts from Pittsburgh.
Spatial data analysis in economics
(2020) Jasny, Johannes; Sousa-Poza, Alfonso
Spatial data analysis has become a widely used tool among economists and social scientists. Improved availability of georeferenced social and economic data, a rising interest in data visualisation, spatial pattern recognition, and spatial interactions as well as improved statistical techniques increased the popularity of spatial data analysis techniques. The purpose of this work is to study spatial data analysis techniques and apply those techniques on social and economic issues. This work consists of three articles on applied spatial data analysis in economics. The first article studies the determinants of local supply differences in the market for election gambling machines (EGM). We study, whether a certain social and economic milieu (e.g. high unemployment) is associated with higher EGM supply. The second article studies spillover effects in the EGM market. The article explains why the EGM supply clusters in certain regions which results in “hot spots” with high gambling supply. Article three evaluates the impact of immigration on the voting behaviour in Germany. As an example, we use the 2015/2016 refugee crisis and study how refugee presence affected the regional election outcomes in the 2016 elections in Germany.
Spatial econometric methods in agricultural economics : selected case studies in German agriculture
(2013) Schmidtner, Eva; Dabbert, Stephan
The location of agricultural activities is determined by location factors that are spatially heterogeneous, such as climate and soil; for the spatial distribution of some agricultural specialties, spatial dependence, i.e., beneficial and self-enhancing effects resulting from a concentration of these agricultural activities, might also play a role. Thus, the dimension ?space? might be of importance in analysing agricultural research settings. This cumulative dissertation consists of three articles addressing current research questions on the spatial distribution of agricultural activities and agricultural profitability in Germany. To account for the geographic location of attributes, spatial econometric analysis tools are used. The first article addresses the determinants of the uneven spatial distribution of organic farming in Germany. In addition to traditional location factors, positive agglomeration effects might also influence the spatially heterogeneous concentration of organic agriculture. Conventional farmers might be more likely to convert to organic farming given an easy communication with organic farmers located nearby and a geographically close and strong institutional network. First, a theoretical model explaining the decision of a farmer to convert from conventional to organic agriculture is established. Next, secondary data at the German county level are analysed by using spatial lag models. Data on organic farming refer to the year 2007. The results suggest that agglomeration effects matter in organic agriculture. For the previous analysis, aggregated data at a relatively low spatial resolution are used, which might lead to results that are artificially generated through the process of data aggregation. The second article addresses the question whether results can be confirmed at different spatial levels, assuming that agglomeration effects are important in organic farming. The results of spatial lag models are compared at two measurement scales, the German counties and community associations. Secondary data are also used in this analysis; for the organic sector, 2007 data are considered. The analysis indicates that essential factors determining the decision to convert from conventional to organic farming are sustained at different spatial resolutions. The results at the lower spatial resolution are shown to be not artificially generated through the aggregation process in this case, which strengthens the relevance of the previous study. The third publication assesses the effects of different indicators of soil characteristics on the estimation results of a Ricardian analysis. The study draws on data from the official farm census conducted in 1999 and on weather data from the German National Meteorological Service at the county level for the time period 1961-1990. Additionally, different soil data bases are considered to control for soil quality. The results of spatial error models suggest that rental prices are determined by climate and non-climate factors. Accounting for different methods of measuring soil quality does not influence the results of the analysis. To estimate the effects of changing climatic conditions on future land rents, data from the regional climate model REMO for the time period 2011-2040 are used. The models show that projected climate levels will have an overall positive but spatially heterogeneous effect on the income from agriculture in Germany. The empirical analyses presented illustrate that spatial econometrics can offer appropriate tools for analysing agriculture. In all three cases theoretical considerations and diagnostic tests for spatial dependence suggest using spatial analysis techniques. The use of alternative specifications of the spatial neighbourhood matrix further supports the stability of results. The general approach and methods used could be translated to other issues in agricultural economics such as potential agglomeration effects in hog production or the future impact of climatic factors on the spatial distribution of viticulture. Thus, spatial econometrics might offer an interesting approach to various spatial research questions in agricultural economics, in addition to the applications that were selected for this thesis.