Democratic Implications of Public Organizations

The author suggests a Weberian methodology, based on theories of democracy and organization, for assessing normative implications of public organizations. How different organizational models contribute to (re)create democracy and legitimacy is scrutinized with reference to a Swedish IT program. The conclusion is that a system management organization will be an appropriate choice for dealing with tame problems, but it will at the same time promote an elitist democratization. In contrast, a development organization will be more appropriate in dealing with complex problems, and it will most likely promote discursive democratization.     

GENDER MATCHING AND COMPETITIVENESS: EXPERIMENTAL EVIDENCE

This paper experimentally investigates if and how people's competitiveness depends on their own gender and on the gender of people with whom they interact. Participants are given information about the gender of the co‐participant they are matched with, they then choose between a tournament or a piece rate payment scheme, and finally perform a real task. As already observed in the literature, we find that significantly more men than women choose the tournament. The gender of the co‐participant directly influences men's choices (men compete less against other men than against women), but only when the gender information is made sufficiently salient. A higher predicted competitiveness of women induces more competition. Giving stronger tournament incentives, or allowing the participants to choose the gender of their co‐participant, increases women's willingness to compete, but does not close the gender gap in competitiveness. (JEL C70, C91, J16, J24, J31, M52)     

Climate riskscapes in world port cities: situating urban‐cosmopolitan risk communities via Ulrich Beck's comparative tactics

Building on empirical research into translocal connections among world port cities in addressing shared challenges of climate risk mitigation and adaptation, in this article I review two widespread tendencies in urban studies – methodological city‐ism and methodological globalism respectively – as a springboard for articulating a methodologically cosmopolitan alternative. This alternative, I argue, involves epistemological issues of how to interrogate ‘the urban’ as assemblages that constitutively draw together the near and the faraway, as well as more practical issues of mobile, multisited, and comparative urban research methods. Empirically, I compare the ways in which urban actors stage global climate risks on the waterfronts of four world cities – Hong Kong, Rotterdam, Yokohama and Copenhagen – to argue that such a comparative tactic of variable ‘riskscapes’ helps situate Ulrich Beck's notion of urban cosmopolitan risk communities more thoroughly into urban studies. In such ways, I suggest, Beck's methodological cosmopolitanism is germane to studying ongoing and far ranging transformation in world political geography, in which transurban networks, communities, and governance arrangements come to complement nation‐state centred institutions. Such conclusions must be tempered, however, by the deployment of Beck's equally strong impetus towards comparative attention to the varieties of second modernity; and doing so, I conclude, aligns well with ongoing transformations in urban studies itself.     

Krylov Sequences as a Tool for Analysing Iterated Regression Algorithms

Abstract.  We use Krylov sequences to analyse a class of regression methods based on successive identification of latent factors. Some results already proved for partial least squares regression (PLSR) are shown to hold for other methods also. We prove that the well-known peculiar pattern of alternating shrinkage and inflation of the principal components is not unique for PLSR. We also show that for any method in the class under study, the coefficient of determination is always at least as high as for principal components regression with the same number of factors.     

Latent Variable Modelling: A Survey*

Abstract. Latent variable modelling has gradually become an integral part of mainstream statistics and is currently used for a multitude of applications in different subject areas. Examples of ‘traditional’ latent variable models include latent class models, item–response models, common factor models, structural equation models, mixed or random effects models and covariate measurement error models. Although latent variables have widely different interpretations in different settings, the models have a very similar mathematical structure. This has been the impetus for the formulation of general modelling frameworks which accommodate a wide range of models. Recent developments include multilevel structural equation models with both continuous and discrete latent variables, multiprocess models and nonlinear latent variable models.     

Lévy‐based Modelling in Brain Imaging

Abstract. A substantive problem in neuroscience is the lack of valid statistical methods for non‐Gaussian random fields. In the present study, we develop a flexible, yet tractable model for a random field based on kernel smoothing of a so‐called Lévy basis. The resulting field may be Gaussian, but there are many other possibilities, including random fields based on Gamma, inverse Gaussian and normal inverse Gaussian (NIG) Lévy bases. It is easy to estimate the parameters of the model and accordingly to assess by simulation the quantiles of test statistics commonly used in neuroscience. We give a concrete example of magnetic resonance imaging scans that are non‐Gaussian. For these data, simulations under the fitted models show that traditional methods based on Gaussian random field theory may leave small, but significant changes in signal level undetected, while these changes are detectable under a non‐Gaussian Lévy model.     

Stratified Case-Cohort Analysis of General Cohort Sampling Designs

Abstract.  It is shown that variance estimates for regression coefficients in exposure-stratified case-cohort studies (Borgan et al ., Lifetime Data Anal., 6, 2000, 39–58) can easily be obtained from influence terms routinely calculated in the standard software for Cox regression. By allowing for post-stratification on outcome we also place the estimators proposed by Chen ( J. R. Statist. Soc. Ser. B , 63, 2001, 791–809) for a general class of cohort sampling designs within the Borgan et al. 's framework, facilitating simple variance estimation for these designs. Finally, the Chen approach is extended to accommodate stratified designs with surrogate variables available for all cohort members, such as stratified case-cohort and counter-matching designs.     

Special theme introduction: methodological cosmopolitanism across the socio‐cultural sciences

The cosmopolitan sociology of Ulrich Beck has been widely recognized as making vital contributions to crosscutting conversations on globalization and transnational studies, including these debates that are being played out on the pages of Global Networks. Beck's impassioned critique of ‘methodological nationalism’ in his own discipline of sociology, in particular, has often served as a springboard for programmatic calls to attend more closely to transnational actors, issues, and processes. However, beyond the occasional acknowledgement, comparatively less attention has been paid so far to the potentialities, specificities, and practicalities of Beck's affirmative alternative vision for the socio‐cultural sciences, that of ‘methodological cosmopolitanism’. Building on and extending out from research experiences obtained in Beck's East Asia and Europe‐focused Cosmopolitan Climate Change (Cosmo‐Climate) project, this special theme brings together experts from across a range of socio‐cultural research fields to discuss and critically interrogate the challenges and capacities of doing methodological cosmopolitanism.