Blog posts

Chapter on party preference, turnout and social cleavages in Germany Wahlen und Wähler

A chapter entitled "Parteiwahl und Nichtwahl: Zur Rolle sozialer Konfliktlinien" has appeared in Wahlen und Wähler: Analysen aus Anlass der Bundestagswahl von 2013 (ed. by Harald Schoen and Bernhard Wessels) and is now available from Springer.

Read more ...

memisc 0.99 published on CRAN

A new version 0.99 of package memisc has been published on CRAN, which adds a few new features to the previously published version.

Read more ...

The long-term relation between turnout and electoral support for social democracts in Germany

At the 5th Annual General Conference of the European Political Science Association I had the opportunity to present a paper entitled "The Crisis of Social Democracy and the Political Demobilisation of the Working Class in Germany". In this paper I analyse the dual decline of turnout in Germany and of the support for the German Social Democratic Party (SPD). I show that both changes are linked and concentrated in a core group of SPD supporters, the manual working class.

Read more ...

AK Wahlen paper on ticket-splitting in Germany

At the Session of the AK "Wahlen und politische Einstellungen (the German specialist group on election, electoral behaviour and political attitudes) I had the opportunity to present a paper on split-ticket voting in Germany. In this paper I find that there is more strategic voting in the direct candidate votes than in the list votes, but that most split-ticket voting appears to be non-strategic.

Read more ...

memisc 0.97 released

Version 0.97 of package memisc has been released to CRAN.

Read more ...

Data set on "Party Positions in Multiple Dimensions across Time and Space" available

Estimates (or more correctly: predictions) of parties' positions in multiple dimensions in different countries, spanning the decades from 1945 (1920 for the USA) to 2010 is now available here on my website.

Read more ...

Estimation techniques: Ordinary least squares and maximum likelihood

A chapter on estimation techniques has appeared in the edited volume Regression Analysis and Causal Inference, edited by Henning Best and Christof Wolf and published by Sage. A companion website is here.

Read more ...

EPSA paper: Inference for multilevel models when the number of clusters is small.

In a recent article published in AJPS it is claimed that Bayesian estimators have a superior performance in the estimation of the influence of group-level covariates, especially if the number of groups/clusters is small. In the paper presented at EPSA, we show that the problems addressed by Bayesian techniques can also be adequately addressed by a frequentist technique, restricted maximum likelihood, without the problems involved in Bayesian estimation, such as the computational cost and the need to select an appropriate prior.

Read more ...