Improving the EM algorithm for mixtures

One of the estimating equations of the Maximum Likelihood Estimation method, for finite mixtures of the one parameter exponential family, is the first moment equation. This can help considerably in reducing the labor and the cost of calculating the Maximum Likelihood estimates. In this paper it is shown that the EM algorithm can be substantially improved by using this result when applied for mixture models. A short discussion about other methods proposed for the calculation of the Maximum Likelihood estimates are also reported showing that the above findings can help in this direction too.     

Institutions and structures as barriers? A comparison of native‐born and immigrant unemployment durations across 12 European countries

This study investigated the effect of institutions on the unemployment duration gap between non‐EU immigrants and native‐born in 12 European countries. Going further than the existing literature, our study encompassed unemployment duration, distinguishing between exits to inactivity, primary and secondary employment. Additionally, we have provided a stronger micro‐foundation to the comparative literature by introducing institutional measures for unemployment‐related benefits at the individual level rather than merely using aggregate proxies. Our analysis found no disincentive effects of benefits for immigrants. Furthermore, the employment prospects of immigrants were better when the demand for low‐skilled labour was high, and immigration policy was labour market‐oriented. In contrast, employment protection legislation did not affect the unemployment duration of immigrants.     

Information and Communication Technologies and the Opportunities of Disabled Persons in the Swedish Labour Market

This article attempts to outline the prospects of disabled persons to gain and retain employment within the Information Society by presenting and discussing the results of a labour market policy programme in Sweden based on information technology. The effects of Information and Communication Technologies (ICTs) for unemployed and employed persons with disabilities can be assessed on the micro, as well as on the macro levels. Technological optimism has given rise to expectations about the great potential of ICTs in creating employment opportunities for disabled persons. Technological optimism, however, derives from a deterministic point of view, i.e. ICTs are regarded as an independent variable. This article suggests that ICTs must be regarded as a variable dependent by the economic, social and cultural order. Its effects on disabled persons employment opportunities are not independent by the power relations at a given time.     

Prosodic cues of identity construction: Intensity in Greek young women's conversational narratives1

The present paper examines the discourse functions of intensity in the context of narrative direct speech quotations. We argue that differentiation in intensity functions as a contextualization cue signalling involvement as well as power negotiation. Intensity, therefore, seems to be an ambivalent signal acquiring its meaning in interaction with other contextual parameters. More specifically, we argue that a louder voice is preferred in in‐group talk representations as a contextualization cue of a high involvement style in conversations between intimate young peers. Lower intensity, on the other hand, is used by young female narrators in the representation of talk with authority‐out‐group figures, as a means of reducing the authority of the adult voices represented in their narratives. The qualitative analysis of our data is further supported by quantitative analysis. We conclude that intensity differentiation in the direct speech quotations of young female narrators functions as a contextualization cue signalling, on the one hand, their independence from adult authority and, on the other, their in‐group bonds.     

The Contribution of Scenic Beauty Indicators in Estimating Environmental Welfare Measures: A Case Study

Aesthetic indicators of landscapes, expressedas individual scenic beauty estimates, may beused as proxies of individuals' specificaesthetic values, and improve the properties ofwelfare estimates produced by contingentvaluation models. This work presents resultsfrom an interdisciplinary study where forestscenic beauty indicators are utilized in aneconomic valuation study approximating welfareestimates from increased forest fireprotection. The omission of scenic beautyindicators from the economic valuation ofenvironmental resources produces biased andoverestimated welfare measures. Combiningeconomic and environmental indicatorssignificantly improves the explanatory power ofeconomic valuation models and of the producedwelfare measures. Such a combination, however,is only possible when carried out byinterdisciplinary research teams. The resultsof such research are significant toenvironmental and natural resource policymakers and planners.     

Multivariate Poisson regression with covariance structure

In recent years the applications of multivariate Poisson models have increased, mainly because of the gradual increase in computer performance. The multivariate Poisson model used in practice is based on a common covariance term for all the pairs of variables. This is rather restrictive and does not allow for modelling the covariance structure of the data in a flexible way. In this paper we propose inference for a multivariate Poisson model with larger structure, i.e. different covariance for each pair of variables. Maximum likelihood estimation, as well as Bayesian estimation methods are proposed. Both are based on a data augmentation scheme that reflects the multivariate reduction derivation of the joint probability function. In order to enlarge the applicability of the model we allow for covariates in the specification of both the mean and the covariance parameters. Extension to models with complete structure with many multi-way covariance terms is discussed. The method is demonstrated by analyzing a real life data set.     

Generalized linear mixed joint model for longitudinal and survival outcomes

Longitudinal studies often entail categorical outcomes as primary responses. When dropout occurs, non-ignorability is frequently accounted for through shared parameter models (SPMs). In this context, several extensions from Gaussian to non-Gaussian longitudinal processes have been proposed. In this paper, we formulate an approach for non-Gaussian longitudinal outcomes in the framework of joint models. As an extension of SPMs, based on shared latent effects, we assume that the history of the response up to current time may have an influence on the risk of dropout. This history is represented by the current, expected, value of the response. Since the time a subject spends in the study is continuous, we parametrize the dropout process through a proportional hazard model. The resulting model is referred to as Generalized Linear Mixed Joint Model (GLMJM). To estimate model parameters, we adopt a maximum likelihood approach via the EM algorithm. In this context, the maximization of the observed data log-likelihood requires numerical integration over the random effect posterior distribution, which is usually not straightforward; under the assumption of Gaussian random effects, we compare Gauss-Hermite and Pseudo-Adaptive Gaussian quadrature rules. We investigate in a simulation study the behaviour of parameter estimates in the case of Poisson and Binomial longitudinal responses, and apply the GLMJM to a benchmark dataset.     

The labour–nature relationship: varieties of labour environmentalism

ABSTRACT

This special issue is a contribution to environmental labour studies, which aims to investigate the practices and theories that integrate labour and nature, by focusing on labour environmentalism. While nature is privately appropriated and exploited by Capital, workers’ organizations tend to construct nature as labour’s other, a place to enjoy or a place to be protected from destruction at best. In the following introductory article to this special issue, we present our view of what environmental labour studies are investigating and might investigate in the future and the place of labour environmentalism within this broader agenda. We also suggest an analytical framework to evaluate the depth, breadth, and level of the agency of the variations of labour environmentalism. We suggest that environmental labour studies can be a way of studying not only the intersections between social and environmental justice, climate change and working conditions but can also contribute to building a bridge between environmental theory and practice.     

Refugees,migrants, neither,both: categorical fetishism and the politics of bounding in Europe’s ‘migration crisis’

The use of the categories ‘refugee’ and ‘migrant’ to differentiate between those on the move and the legitimacy, or otherwise, of their claims to international protection has featured strongly during Europe’s ‘migration crisis’ and has been used to justify policies of exclusion and containment. Drawing on interviews with 215 people who crossed the Mediterranean to Greece in 2015, our paper challenges this ‘categorical fetishism’, arguing that the dominant categories fail to capture adequately the complex relationship between political, social and economic drivers of migration or their shifting significance for individuals over time and space. As such it builds upon a substantial body of academic literature demonstrating a disjuncture between conceptual and policy categories and the lived experiences of those on the move. However, the paper is also critical of efforts to foreground or privilege ‘refugees’ over ‘migrants’ arguing that this reinforces rather than challenges the dichotomy’s faulty foundations. Rather those concerned about the use of categories to marginalise and exclude should explicitly engage with the politics of bounding, that is to say, the process by which categories are constructed, the purpose they serve and their consequences, in order to denaturalise their use as a mechanism to distinguish, divide and discriminate.