Relatioinships between economic and statistical price indices

In the following, the economic counterparts of Eichhorn's and Voeller's tests for statistical price indices will be studied. We will see that replacing the statistical Commensurability Axiom in the economic price index theory by a property which is only concerned with price changes leads to similar relationships between this one and several other tests as in the statistical price index theory.     

The effects of propensity score weighting on attrition biases in attitudinal,behavioral, and socio-demographic variables in a short-term web-based panel survey

Propensity score weighting often is used to correct for attrition biases in panel surveys. While methodological literature exists on the logic of propensity score weighting and its practical applications, an in-depth discussion is lacking on the effects of using this weighting to correct for attrition biases in attitudinal, behavioral, and socio-demographic variables. By applying a split panel design, we assessed the effects of weighting on attrition biases in 48 attitudinal, 38 behavioral, and 27 socio-demographic variables. Our findings suggest – while acknowledging the estimate-specific nature of bias – first, that biases vary across these types of variables and second, that the effects of propensity score weighting are not homogeneous across the types. Accordingly, a sole reliance on socio-demographics to evaluate attrition in the present panel survey would have resulted in an underestimation of the biases of attitudinal variables and an overestimation of the ability of weighting to cure the negative effects of attrition in behavioral variables.     

Gedenken an Prof. Dr. rer. nat., Dipl.-Psych. Ernst Timaeus

Ohne Zusammenfassung     

Thinning operations for modeling time series of counts—a survey

The analysis of time series of counts is an emerging field of science. To obtain an ARMA-like autocorrelation structure, many models make use of thinning operations to adapt the ARMA recursion to the integer-valued case. Most popular among these probabilistic operations is the concept of binomial thinning, leading to the class of INARMA models. These models are proved to be useful, especially for processes of Poisson counts, but may lead to difficulties in the case of different count distributions. Therefore, several alternative thinning concepts have been developed. This article reviews such thinning operations and shows how they are successfully applied to define integer-valued ARMA models.     

Optimal design for the Bradley–Terry paired comparison model

Paired comparisons are a popular tool for questionnaires in psychological marketing research. The quality of the statistical analysis of the responses heavily depends on the design, i.e. the choice of the alternatives in the comparisons. In this paper we show that the structure of locally optimal designs changes substantially with the parameters in the underlying utility. This fact is illustrated by elementary examples, where the optimal designs can be completely characterized. As an alternative maximin efficient designs are proposed which perform well for all parameter settings. Research supported by grant Ho 1286 of the German Research Council (Deutsche Forschungsgemeinschaft).     

Das Eignungsfeststellungsverfahren für angehende Hauptfachstudierende der Soziologie

This article presents preliminary experience with a selection procedure for the diploma study course in sociology at the LMU Munich, which was first implemented in the winter term 2004/05. Furthermore, it examines the consequences of this procedure. The selection procedure, which is limited in time, was established due to high discontinuation rates and a remarkable congestion of the scientific personnel who are particularly involved in the foundation courses. Judicial fundament of the procedure is an “experimental clause” in the Bavarian University Act. First of all we point out that the number of newly registered undergraduates remarkably declined. Even the total number of applicants is lower than in the years before the initiation of the selection procedure. Secondly, we consider the dwindling during the process of the selection procedure. Contrary to some apprehensions it is obvious that applicants with a good university-entrance diploma do not choose possible alternatives, but still consider the diploma study course in sociology. Concerning the overall evaluation of the selection procedure’s consequences our results show thirdly, that the procedure is highly accepted by all parties concerned and that it therefore has to be regarded as an efficient solution to lower the discontinuation rates as well as to cope with the capacity overload.