We introduce archetypal analysis as a tool to describe and categorize scientists. This approach identifies typical characteristics of extreme ('archetypal') values in a multivariate data set. These positive or negative contextual attributes can be allocated to each scientists under...

The use of large datasets for macroeconomic forecasting has received a great deal of interest recently. Boosting is one possible method of using high-dimensional data for this purpose. It is a stage-wise additive modelling procedure, which, in a linear specification, becomes a variable selection...

An ongoing debate in the literature on efficiency of higher education institutions concerns the indicator for research output in the empirical analysis. While several studies chose to use the number of publications, others rely on the overall amount of research grants. The present study...

Im letzten Teil der dreiteiligen Artikelserie zu regionalen Konjunkturzyklen in Deutschland wird untersucht, ob die Wirtschaftszyklen der Bundesländer im Zeitverlauf ähnlicher werden, d.h. konvergieren. Aufbauend auf Teil II werden zunächst die für alle Bundesländer berechneten Wendepunkte...

The Ifo Institute for Economic Research has been conducting regular business surveys since its foundation in 1949. The most well-known of Ifo's surveys is the Ifo Business Survey (ifo Konjunkturtest). The micro data of the Ifo Business Survey are accessible to external researchers on-site at Ifo...

In this paper we present the Ifo Investment Database, which provides annual investment data for 12 investment assets in 50 German industries from 1991 onward. The data is consistent with national accounts statistics provided by the German Federal Statistical Office and is based on investments in...

The use of large datasets for macroeconomic forecasting has received a great deal of interest recently. Boosting is one possible method of using high-dimensional data for this purpose. It is a stage-wise additive modelling procedure, which, in a linear specification, becomes a variable selection...