Gerhard Sonnert und Gerald Holton: What happened to the children who fled nazi persecution

KZfSS Kölner Zeitschrift für Soziologie und Sozialpsychologie -     

Encompassing and indirect inference

Summary In the literature on encompassing [see e.g. Mizon-Richard (1986), Hendry-Richard (1990), Florens-Hendry-Richard (1987)] there is a basic contradiction: on the one hand it is said that it is not possible to assume that the true distribution belongs to one of two competing modelM ₁ andM ₂, but, on the other hand, this assumption is made in the study of encompassing tests. In this paper we first propose a formal definition of encompassing, we then briefly examine the properties of this notion and we propose encompassing tests which do not assume that the true distribution belongs toM ₁ orM ₂; these tests are based on simulations. Finally, generalizing an idea used in the definition of an encompassing test (the GET test) we propose a new kind of inference, called indirect inference, which allows for estimation and test procedures when the model is too complicated to be treated by usual methods (for instance maximum likelihood methods); the only assumption made on the model is that it can be simulated, which seems to be a minimal requirement. This new class of inference methods can be used in a large number of domains and some examples are given. The present paper is based on Gouriéroux-Monfort (1992), and Gouriéroux-Monfort-Renault (1993), respectively GM and GMR hereafter. Invited paper at the Conference on ?Statistical Tests: Methodology and Econometric Applications?, held in Bologna, Italy, 27–28 May 1993.     

Ethnography as Translation

Sociologists and anthropologists often struggle over how to accurately convey ethnographic data from the field setting to a final report. This paper examines ethnography as a form of translation in order to clarify what occurs between the acquisition of data and the formulation of a thesis about the data. The paper argues that the ethnographers mind should be seen as a transitional space which in the act of translating field data into an analytic report (1) poses unique challenges to ethnographys claims for providing an accurate account of field situations while (2) simultaneously offering paths to insight which quantitative and survey research can not.     

Is the SOGS an Accurate Measure of Pathological Gambling Among Children, Adolescents and Adults?

The South Oaks Gambling Screen (SOGS) is widely used to assess the prevalence of pathological gambling. For a variety of reasons, this instrument may not provide an accurate rate of the prevalence of pathological gambling. In this paper, one source of error in data provided by the SOGS is investigated. It is argued that individuals may not fully understand the meaning of some items, and that clarification of the meaning of misunderstood items may in some cases lead to a changed score on the scale. The present study evaluates respondents' understanding of the SOGS items. The results from three studies are reported, each using a different sample: grade school children, adolescents and adults. It was hypothesised that (1) participants would not understand some items of the SOGS, (2) problem gamblers and probable pathological gamblers would be more inclined to interpret items incorrectly than would non-problem gamblers and, (3) consistent with the first two hypotheses, clarification of items would decrease the number of participants identified as problem gamblers or probable pathological gamblers. The data obtained supported hypotheses 1 and 3. Furthermore, hypothesis 2 was supported for grade school children, but not for adolescents or adults. These results are consistent with recent literature on endorsement and acquiescence phenomena, and have implications for prevalence studies of probable pathological gambling.     

Adaptive importance sampling in general mixture classes

In this paper, we propose an adaptive algorithm that iteratively updates both the weights and component parameters of a mixture importance sampling density so as to optimise the performance of importance sampling, as measured by an entropy criterion. The method, called M-PMC, is shown to be applicable to a wide class of importance sampling densities, which includes in particular mixtures of multivariate Student t distributions. The performance of the proposed scheme is studied on both artificial and real examples, highlighting in particular the benefit of a novel Rao-Blackwellisation device which can be easily incorporated in the updating scheme. This work has been supported by the Agence Nationale de la Recherche (ANR) through the 2006–2008 project ’ . Both last authors are grateful to the participants to the BIRS meeting on “Bioinformatics, Genetics and Stochastic Computation: Bridging the Gap”, Banff, for their comments on an earlier version of this paper. The last author also acknowledges an helpful discussion with Geoff McLachlan. The authors wish to thank both referees for their encouraging comments.