Institute for Employment Research IAB
Institute for Employment Research IAB
Patuelli R.,University of Lugano |
Patuelli R.,The Rimini Center for Economic Analysis |
Reggiani A.,University of Bologna |
Nijkamp P.,VU University Amsterdam |
Schanne N.,Institute for Employment Research IAB
Journal of Geographical Systems | Year: 2011
In this paper, we present a review of various computational experiments concerning neural network (NN) models developed for regional employment forecasting. NNs are nowadays widely used in several fields because of their flexible specification structure. A series of NN experiments is presented in the paper, using two data sets on German NUTS-3 districts. Individual forecasts are computed by our models for each district in order to answer the following question: How relevant are NN parameters in comparison to NN structure? Comprehensive testing of these parameters is limited in the literature. Building on different specifications of NN models-in terms of explanatory variables and NN structures-we propose a systematic choice of NN learning parameters and internal functions by means of a sensitivity analysis. Our results show that different combinations of NN parameters provide significantly varying statistical performance and forecasting power. Finally, we note that the sets of parameters chosen for a given model specification cannot be light-heartedly applied to different or more complex models. © 2010 Springer-Verlag.
Patuelli R.,University of Bologna |
Patuelli R.,The Rimini Center for Economic Analysis |
Schanne N.,Institute for Employment Research IAB |
Griffith D.A.,University of Texas at Dallas |
And 2 more authors.
Journal of Regional Science | Year: 2012
The geographical distribution and persistence of regional/local unemployment rates in heterogeneous economies (such as Germany) have been, in recent years, the subject of various theoretical and empirical studies. Several researchers have shown an interest in analyzing the dynamic adjustment processes of unemployment and the average degree of dependence of the current unemployment rates or gross domestic product from the ones observed in the past. In this paper, we present a new econometric approach to the study of regional unemployment persistence, in order to account for spatial heterogeneity and/or spatial autocorrelation in both the levels and the dynamics of unemployment. First, we propose an econometric procedure suggesting the use of spatial filtering techniques as a substitute for fixed effects in a panel estimation framework. The spatial filter computed here is a proxy for spatially distributed region-specific information (e.g., the endowment of natural resources, or the size of the "home market") that is usually incorporated in the fixed effects coefficients. The advantages of our proposed procedure are that the spatial filter, by incorporating region-specific information that generates spatial autocorrelation, frees up degrees of freedom, simultaneously corrects for time-stable spatial autocorrelation in the residuals, and provides insights about the spatial patterns in regional adjustment processes. We present several experiments in order to investigate the spatial pattern of the heterogeneous autoregressive coefficients estimated for unemployment data for German NUTS-3 regions. We find widely heterogeneous but generally high persistence in regional unemployment rates. © 2012, Wiley Periodicals, Inc.
Geiss C.,German Aerospace Center |
Geiss C.,Humboldt University of Berlin |
Taubenbock H.,German Aerospace Center |
Tyagunov S.,German Research Center for Geosciences |
And 3 more authors.
Earthquake Spectra | Year: 2014
This paper quantitatively evaluates the suitability of multi-sensor remote sensing to assess the seismic vulnerability of buildings for the example city of Padang, Indonesia. Features are derived from remote sensing data to characterize the urban environment and are subsequently combined with in situ observations. Machine learning approaches are deployed in a sequential way to identify meaningful sets of features that are suitable to predict seismic vulnerability levels of buildings. When assessing the vulnerability level according to a scoring method, the overall mean absolute percentage error is 10.6%, if using a supervised support vector regression approach. When predicting EMS-98 classes, the results show an overall accuracy of 65.4% and a kappa statistic of 0.36, if using a naive Bayes learning scheme. This study shows potential for a rapid screening assessment of large areas that should be explored further in the future. © 2014, Earthquake Engineering Research Institute.
Burr H.,Federal Institute for Occupational Safety and Health BAuA |
Rauch A.,Institute for Employment Research IAB |
Rose U.,Federal Institute for Occupational Safety and Health BAuA |
Tisch A.,Institute for Employment Research IAB |
Tophoven S.,Institute for Employment Research IAB
International Archives of Occupational and Environmental Health | Year: 2015
Purpose: We investigated whether (1) current employment status (regular full-time, regular part-time and marginal employment) is associated with depressive symptoms and (2) whether these associations are mediated by current working conditions and previous employment history. Methods: Two cohorts of German employees aged 46 and 52 years were selected from administrative data of the German Federal Employment Agency and answered questions about depressive symptoms (we use an applied version of BDI-V) and their current working conditions. In addition, the participants gave written consent to link register data regarding their employment histories (n = 4,207). Multiple linear regression analyses were conducted. Results: Men experienced elevated depressive symptoms when working regular part-time; women experienced such symptoms when engaged in marginal employment. These associations decreased when we adjusted for job insecurity and rose slightly when we adjusted for leadership quality. Men and women who reported a low level of influence at work showed a higher risk of depressive symptoms. For women, the association between current employment position and depressive symptoms could be partly explained by low levels of influence at work. For men, the association between depressive symptoms and current regular part-time employment decreased when we adjusted for previous part-time employment. Conversely, for women, the association with depressive symptoms increased in current regular part-time and marginal employment when we adjusted for employment history. Conclusions: In both genders, the observed associations between depressive symptoms and current employment status were mediated by both current psychosocial conditions and employment history. Employees not having a regular full-time job differed from full-time employees with respect to both their current working conditions and their employment history. © 2014, The Author(s).
Daraio C.,University of Bologna |
Bonaccorsi A.,University of Pisa |
Geuna A.,University of Turin |
Geuna A.,Grenoble Graduate School of Business |
And 22 more authors.
Research Policy | Year: 2011
This paper provides a new and systematic characterization of 488 universities, from 11 European countries: Finland, France, Germany, Hungary, Italy, Netherlands, Norway, Portugal, Spain, Switzerland and UK. Using micro indicators built on the integrated Aquameth database, we characterize the European university landscape according to the following dimensions: history/foundation of university, dynamics of growth, specialization pattern, subject mix, funding composition, offer profile and productivity. © 2010 Elsevier B.V. All rights reserved.
Kubis A.,Institute for Employment Research IAB |
Schneider L.,Coburg University of Applied Sciences |
Schneider L.,Halle Institute for Economic Research IWH
Regional Studies | Year: 2015
Kubis A. and Schneider L. Regional migration, growth and convergence – a spatial dynamic panel model of Germany, Regional Studies. This paper empirically analyses the question of how regional migration affects regional convergence and growth in post-reunification Germany. Addressing the endogeneity of migration and human capital, a dynamic panel data model within the framework of β-convergence is applied, accounting for spatial effects. The regressions indicate that out-migration has a negative but modest effect on regional growth; the expected effect of skill selection is only partly confirmed. In the East German subsample, in-migration increases growth independently of its human capital effect; in West Germany, in-migration lowers growth per se, but this negative impact is offset by the growth-stimulating forces of migrants’ skills. © 2015 Regional Studies Association
Kropp P.,Institute for Employment Research |
Schwengler B.,Institute for Employment Research IAB
Regional Studies | Year: 2014
Kropp P. and Schwengler B. Three-step method for delineating functional labour market regions, Regional Studies. This paper proposes a new three-step method to find delineations that adequately define functional regions with strong interactions within the region and few connections with outside areas based on commuting flows. A graph-theoretical approach is used to create many meaningful delineations for labour market regions in Germany and the modularity concept from network analysis is employed to select the delineation that captures the commuting flows best. As a result, a delineation of 50 German labour market regions that are quite heterogeneous in terms of size is obtained. Using the modularity measure, the current delineation is compared with previous functional delineations. © 2014 © 2014 Regional Studies Association.
Granato N.,University of Mannheim |
Haas A.,Institute for Employment Research IAB |
Hamann S.,Institute for Employment Research IAB |
Niebuhr A.,Institute for Employment Research IAB |
Niebuhr A.,University of Kiel
Journal of Regional Science | Year: 2015
Differences in regional unemployment are still pronounced in Germany, especially between eastern and western Germany. Although the skill level seems important for the relationship between regional disparities and labor migration, corresponding empirical evidence is scarce. Applying dynamic panel models, we investigate the impact of labor mobility differentiated by educational attainment of the workers on regional unemployment disparities between 2000 and 2008. The impact of low- and medium-skilled migration is consistent with traditional neoclassical reasoning, suggesting that labor mobility reduces differences in regional unemployment rates. In contrast, the migration of high-skilled workers tends to reinforce disparities. © 2015 Wiley Periodicals, Inc.
Sowa F.,Institute for Employment Research IAB
Polar Record | Year: 2015
In recent years, a decline in the consumption of local foods (kalaalimernit) can be observed in Greenland. However, its appreciation and symbolisation is increasing and kalaalimernit are a powerful contemporary symbol for being Greenlandic. The present article argues that kalaalimernit, as a specifically Greenlandic taste, are suited to marking and maintaining a cultural boundary in relation to the Danish people living in the country, a boundary constructed through identity politics. As the empirical findings from fieldwork conducted in the Greenlandic capital Nuuk and the small coastal settlement Oqaatsut demonstrate, this construction is subject to social change. Greenlanders advocate two different narrative patterns regarding how kalaalimernit are to be understood that stem from contemporary definitional struggles over what kind of cultural boundary is deemed important to demarcate. The struggle illustrates two different perceptions of Greenland as either an indigenous people and/or a small Nordic nation. Copyright © Cambridge University Press 2014.
Eckman S.,Institute for Employment Research IAB
Social Science Computer Review | Year: 2016
The LISS online panel has made extra efforts to recruit and retain households that were not regular users of the Internet into the study. Households were provided with computers and/or Internet when necessary. Including these cases made the panel more representative of the Dutch population, by bringing in respondents who were more likely to be older, to live in single-person homes, and to have migration backgrounds. This article replicates five published articles that used LISS data and explores how the conclusions in these articles would have been different had the LISS panel not included the non-Internet households. There are strong demographic differences between the Internet and non-Internet households, and estimates of means would in many cases be biased if these households had not been included. However, across the five replicated studies, few of the published model estimates are substantively affected by the inclusion of these households in the LISS sample. © 2015, The Author(s) 2015.