Parameter Estimation in Pair-hidden Markov Models

Abstract.  This paper deals with parameter estimation in pair-hidden Markov models. We first provide a rigorous formalism for these models and discuss possible definitions of likelihoods. The model is biologically motivated and therefore naturally leads to restrictions on the parameter space. Existence of two different information divergence rates is established and a divergence property is shown under additional assumptions. This yields consistency for the parameter in parametrization schemes for which the divergence property holds. Simulations illustrate different cases which are not covered by our results.     

Turbulences in the Climate of Opinion: Methodological Applications of the Spiral of Silence Theory

New tools for measuring changes in public opinion can be derivedfrom the theory of the spiral of silence. Measures of individualassessment of the climate of opinion and of confidence aboutshowing one's own opinion document the processes by which thelosing side falls increasingly silent and the winning side istherefore overrated.     

Transnational lives,transnational marriages: a review of the evidence from migrant communities in Europe

Abstract Whom do migrants marry? This question has become a popular topic of research, and existing studies identify a common trend: most of the non‐European, non‐Christian migrants in Europe marry someone from their country of origin. The motivations for such practices are to be found in the characteristics of transnational spaces and in the social structures that emerge in such spaces. Based on a review of research from several European countries, three such constellations are discussed: first, the obligations to kin, especially when migration regulations become more restrictive, and marriage becomes the last route by which to migrate to Europe. Second, new forms of global inequality, between the metropolitan centre and countries of the global periphery, give migrants in Europe improved status and standing in their society of origin and therefore excellent opportunities on the marriage market there. Third, gender relations have started to shift in both host society and migrant families. Men and women alike are trying to rebalance power relations within marriage and to shift them in their favour. In this process marriage to a partner from the country of family origin may promise strategic benefits. The article ends with suggestions for future research.     

RATING SCALES NUMERIC VALUES MAY CHANGE THE MEANING OF SCALE LABELS

Three experiments indicate that the numeric values providedas part of a rating scale may influence respondents' interpretationof the endpoint labels. In experiment 1, a representative sampleof German adults rated their success in life along an 11-pointrating scale, with the endpoints labeled "not at all successful"and "extremely successful." When the numeric values ranged from0 ("not at all successful") to 10 ("extremely successful"),34 percent of the respondents endorsed values between 0 and5. However, only 13 percent endorsed formally equivalent valuesbetween –5 and 0, when the scale ranged from –5("not at all successful") to +5 ("extremely successful"). Experiment2 provided an extended conceptual replication of this finding,and experiment 3 demonstrates that recipients of a respondent'sreport draw different inferences from formally equivalent butnumerically different values. In combination, the findings indicatethat respondents use the numeric values to disambiguate themeaning of scale labels, resulting in different interpretationsand, accordingly, different subjective scale anchors.     

The Public Opinion Research Correspondent

This essay outlines a contract concluded by the leading Germannewspaper, Frankfurter Allgemeine, and the Allensbach Institutfür Demoskopie which breaks new ground in journalism bycreating the position of the public opinion research correspondent.     

The Chairperson of Child Care Reviews in Scotland: Implications for the Role of Reviews in the Decision Making Process

Correspondence to Dr A. J. Kendrick, Research Fellow, Department of Political Science and Social Policy, University of Dundee, Dundee DD1 4HN, Scotland. Summary This article is based upon the first stage of a research projecton statutory child care reviews in Scotland and explores therole of reviews in the decision-making processes for childrenin local authority care. We have argued that the position ofchairperson of reviews has an important role in locating childcare reviews in the organïzational structures of the SocialWork Departments. The designation of the chairperson also hasimplications for the objectivity of the child care review. Thenature of conclusions of child care reviews is also exploredand we show that this is a complex issue reflecting the childcare review's relationships to other decision-making bodiesand the manner in which the delegation of authority for thechairing of reviews is structured. While this research is basedupon the twelve Scottish Social Work Departments we believethat the issues discussed have a general relevance.     

The Selection of the Children's Panel for the County of Fife: A Case Study

Summary This paper examines the process of selecting Children's Panelmembers for one Scottish County in the light of the two separateprinciples on which the new system is based. It shews that wherethese were in conflict the Advisory Committee chose candidatessuitable for the task to be performed rather than those whowould compose a Panel representative of the community. The paperargues that this approach to the problem of panel selectionwas valid     

Joint Estimation of Intersecting Context Tree Models

We study a problem of model selection for data produced by two different context tree sources. Motivated by linguistic questions, we consider the case where the probabilistic context trees corresponding to the two sources are finite and share many of their contexts. In order to understand the differences between the two sources, it is important to identify which contexts and which transition probabilities are specific to each source. We consider a class of probabilistic context tree models with three types of contexts: those which appear in one, the other, or both sources. We use a BIC penalized maximum likelihood procedure that jointly estimates the two sources. We propose a new algorithm which efficiently computes the estimated context trees. We prove that the procedure is strongly consistent. We also present a simulation study showing the practical advantage of our procedure over a procedure that works separately on each data set.