A test for the parametric form of the variance function in a partial linear regression model

We consider the problem of testing for a parametric form of the variance function in a partial linear regression model. A new test is derived, which can detect local alternatives converging to the null hypothesis at a rate n^-1/2$n^{-1/2}$ and is based on a stochastic process of the integrated variance function. We establish weak convergence to a Gaussian process under the null hypothesis, fixed and local alternatives. In the special case of testing for homoscedasticity the limiting process is a scaled Brownian bridge. We also compare the finite sample properties with a test based on an L²$L^2$-distance, which was recently proposed by You and Chen [2005. Testing heteroscedasticity in partially linear regression models. Statist. Probab. Lett. 73, 61–70].     

Information Needs Concerning a Planned Waste Incineration Facility

Waste management has become a major environmental issue in Germany. The siting of waste incineration especially arouses strong local opposition. The study presented here is related to such a case (i.e., a planned waste incineration facility in a small West German village). The study is based on a telephone survey aimed at the information needs of the residents. Two topics are stressed: (1) the thematic relevance of the siting project as seen by the public; and (2) the residents'information needs. The results show that a majority of residents are concerned about the planned facility, and the most important topics of their information needs refer to the risks and the safety systems of the planned facility, as well as information about waste management alternatives. Furthermore, the information needs depend on the personal relevance of the issue and the perceived knowledge deficit about it. Conclusions are drawn with regard to the design of a risk communication program. Here, four groups of residents are distinguished in terms of knowledge and motivation and, thus, need to be approached in different ways.     

Using latent class analysis to detect behavioral patterns in systems of observational variables

Behavioral observation is widely used for data gathering in evaluation research. Yet it leaves the investigator with unique problems. Usually, multiple observations result in a hierarchical data set, where numerous data records exist for each subject. Researchers face data reduction problems at least at two levels. First, there is the well-known and often-addressed problem of reducing the number of variables in a data set with only one information record per individual. Second, there is the problem of summarizing data at the individual subject level. The easiest way to perform this latter type of aggregation involves using univariate summary measures as probabilities of “using” an item, means, or standard deviations for each item per subject. Other standard procedures include first order interactions between pairs of items. However, use of pair-wise interactions is restricted because of variable dependence within each subject (this Affects e.g. factor analysis), or because of the relatively high number of single observations (this Affects e.g., cluster analysis). In this paper we propose employing Latent Class Analysis (LCA) to reduce the amount of information in observational data sets. In a first step, LCA allows one to specify intraindividual behavior patterns. In a second step, LCA allows one to derive meaningful summary scores for each individual. The two steps are illustrated using data that describe peer play competence in Swedish toddlers.     

E-optimal designs for regression models with quantitative factors— a reasonable choice?

For regression models with quantitative factors it is illustrated that the E-optimal design can be extremely inefficient in the sense that it degenerates to a design which takes all observations at only one point. This phenomenon is caused by the different size of the elements in the covariance matrix of the least-squares estimator for the unknown parameters. For these reasons we propose to replace the E-criterion by a corresponding standardized version. The advantage of this approach is demonstrated for the polynomial regression on a nonnegative interval, where the classical and standardized E-optimal designs can be found explicitly. The described phenomena are not restricted to the E-criterion but appear for nearly all optimality criteria proposed in the literature. Therefore standardization is recommended for optimal experimental design in regression models with quantitative factors. The optimal designs with respect to the new standardized criteria satisfy a similar invariance property as the famous D-optimal designs, which allows an easy calculation of standardized optimal designs on many linearly transformed design spaces.     

Homo neurooeconomicus

Some years ago researchers in economics have started to adopt neurological techniques like functional magnetic resonance imaging (fMRI) especially in game theoretic research-settings founded on mainstream rational choice theory. They aim to pinpoint neural activities in human brains while exposing individuals to certain stimuli (social dilemma games, choices of brands or impact of commercials). To their surprise researchers find parts of human brains involved in the observed decision making processes that normally generate emotions or are designed to store culturally acquired social preferences. In other words: neoclassical rational choice theory is discovering emotions, neural correlates of cultural predispositions and other non rational strategies of decision making processes in human brains. These findings that are acclaimed as a paradigmatic revolution and nonetheless interpreted as a confirmation of the leading rank of economics in social sciences are increasingly fascinating representatives of management and marketing. The pragmatic illusion of shortcuts into consumer brains has led to the inauguration of a specious variation of neuroeconomics named ?neuro-marketing”. Neither the admonition of leading neuroscientists and neuroeconomists nor the apparent triviality of most of the results are accounted for. Beyond this neoclassical rational choice theorist ignore the underlying scientific as well as pragmatic messages of these observations: the fact that sociology, economics, psychology and neuroeconomics tend to mutually validate their respective findings as social correlates of brain-activities and vice versa.     

Addendum to the Paper,Bayesian D-Optimal and Model Robust Designs in Linear Regression Models

In the recent paper of Dette (1993) there are two figures missing which will be given in this addendum.     

Patent portfolios for strategic R&D planning

Empirical research has found a discrepancy between the perceived importance and the actual level of information on competitor's R&D strategies. It has been argued in the literature that patent information might be used to overcome this information deficit. However, empirical research further reveals that patent information is rarely used in strategic R&D planning. The present paper explores this issue and introduces two types of patent portfolios for strategic R&D planning. In patent portfolios on the company level, patenting strategies are identified and the quality of overall technological positions is benchmarked against relevant competitors. In addition, we present a patent portfolio on the technological level, which, as it is known from various technology portfolios, helps companies to manage the allocation of R&D resources effectively. Based on patent data from 21 German, European and Japanese mechanical engineering companies we show the application of both patent portfolios for strategic R&D planning purposes. The patent portfolios prove to be a very valuable tool for R&D decision makers in companies. Based on the experiences made in the case study, recommendation for the effective use of patent portfolios are formulated.     

Psychological stress-factors and concentration of immunoglobulins and complement components in Norwegian nurses

Psychological stress produces immunological changes in animals, and increasing evidence suggests that this may also be true for humans. In the present study of 34 nurses in a busy ward of a Norwegian hospital, significant relationships have been demonstrated between die plasma levels of immunoglobulins and complement components and work-related 'stress', anxiety, and cognitive defence strategies. The main components of die work-related stress experience were role-stress and nonparticipation in decision-making.

The results indicate chat immunological parameters may perhaps be used as a psychological stress indicator, but the relationships are complex and can best be understood if individual coping and defence mechanisms are considered. Health symptoms were also examined, but these were not related to stress experience or immunological measures.