Model-based clustering with non-elliptically contoured distributions

The majority of the existing literature on model-based clustering deals with symmetric components. In some cases, especially when dealing with skewed subpopulations, the estimate of the number of groups can be misleading; if symmetric components are assumed we need more than one component to describe an asymmetric group. Existing mixture models, based on multivariate normal distributions and multivariate t distributions, try to fit symmetric distributions, i.e. they fit symmetric clusters. In the present paper, we propose the use of finite mixtures of the normal inverse Gaussian distribution (and its multivariate extensions). Such finite mixture models start from a density that allows for skewness and fat tails, generalize the existing models, are tractable and have desirable properties. We examine both the univariate case, to gain insight, and the multivariate case, which is more useful in real applications. EM type algorithms are described for fitting the models. Real data examples are used to demonstrate the potential of the new model in comparison with existing ones.     

Social epigenetics: a science of social science?

Epigenetics has considerable potential to transform social science by embedding mutually regulative reciprocal connections between biological and social processes within the human activities it studies. This paper highlights common epigenetic methods and outlines practical considerations in the design of ‘social epigenetics’ research addressing the identification of biomolecular pathways, statistical inference of causality, conceptualization of the environment as a biochemical event, heritability of epigenetic alterations and intergenerational accountability, and concept of time implied by attempts to capture complex, non-linear gene-environment interactions. Finally, we reflect on the social epigenome as a conceptual space and try to identify barriers to translation, and practical and ethical issues raised by epigenetics research. In order for social epigenetics and social science to contribute to the emergence of this putative ‘science of social science’ and to capture meaningful human experience they will both need to change significantly.     

A FINE-TUNED ESTIMATOR OF A GENERAL CONVERGENCE RATE

A general rate estimation method based on the in‐sample evolution of appropriately chosen diverging/converging statistics has recently been proposed by D.N. Politis [C. R. Acad. Sci. Paris, Ser. I, vol. 335, pp. 279–282, 2002] and T. McElroy & D.N. Politis [Ann. Statist., vol. 35, pp. 1827–1848, 2007]. In this paper, we show how a modification of the original estimators achieves a competitive rate of convergence. The modified estimators require the choice of a tuning parameter; an optimal such choice is generally a non‐trivial problem in practice. Some discussion to that effect is given, as well as a small simulation study in a heavy‐tailed setting.     

Managing Supply Disruptions when Sourcing from Reliable and Unreliable Suppliers

We study a manufacturer's optimal multiple‐sourcing strategies when some but not all suppliers face risks of complete supply disruptions. Using an approximate model, we show that the optimal unreliable orders are ranked by a simple and intuitive criterion, and are invariant of minor market size changes. Furthermore, when ordering from one reliable and one unreliable supplier, we show that the total order quantity and its allocation between the two suppliers are independent decisions. We then test and confirm the robustness of the insights without the approximation, as well as when we relax various assumptions.     

Reorganizing Social Policies through Social Partnerships: Greece in European Perspective

In postwar Western Europe social policies in the wider sense relied in many countries on neo‐corporatist policies of implementation. Since the 1980s such policies have ceased to be as dominant as they used to be, being associated with what has been called “policy communities” and “policy networks”. As far as the reforms pursued by many countries in order to readjust their economies and labour markets are concerned, significant shifts of such a kind were observed. Illustrations of these trends are presented in a comparative section. We attempt to demonstrate the dual structures of social policy formation and implementation, i.e. neo‐corporatist and network/policy community policies, and to discuss the “how” of such policies, i.e. their “raison d’être” and their “real world” enforcement. Against a background of various semi‐corporatisms and adversarial trade union politics, Greece is trying at the moment to adopt this pattern in several social policy areas, though this is not yet quite visible. Neo‐corporatism is also enhanced. We attempt to show where neo‐corporatism is tried (e.g. certain “social dialogue” structures) and where policy communities are encouraged (e.g. public health, local social policies, etc.). Sometimes the boundaries between the two systems are blurred, with some social dialogue committees appearing as quasi‐policy communities. Finally we endeavour to examine the outcomes of such policies and to see their inner logic against the theoretical background. The concept of multilevel governance as a wider policy instrument which incorporates both the above systems is of special interest here.     

Valid Resampling of Higher-Order Statistics Using the Linear Process Bootstrap and Autoregressive Sieve Bootstrap

We show that the linear process bootstrap (LPB) and the autoregressive sieve bootstrap (AR sieve) are, in general, not valid for statistics whose large-sample distribution depends on moments of order higher than two, irrespective of whether the data come from a linear time series or not. Inspired by the block-of-blocks bootstrap, we circumvent this non-validity by applying the LPB and AR sieve to suitably blocked data and not to the original data itself. In a simulation study, we compare the LPB, AR sieve, and moving block bootstrap applied directly and to blocked data.     

Evaluation of Linear Trend Tests Using Resampling Techniques

A number of parametric and non-parametric linear trend tests for time series are evaluated in terms of test size and power, using also resampling techniques to form the empirical distribution of the test statistics under the null hypothesis of no linear trend. For resampling, both bootstrap and surrogate data are considered. Monte Carlo simulations were done for several types of residuals (uncorrelated and correlated with normal and nonnormal distributions) and a range of small magnitudes of the trend coefficient. In particular for AR(1) and ARMA(1, 1) residual processes, we investigate the discrimination of strong autocorrelation from linear trend with respect to the sample size. The correct test size is obtained for larger data sizes as autocorrelation increases and only when a randomization test that accounts for autocorrelation is used. The overall results show that the type I and II errors of the trend tests are reduced with the use of resampled data. Following the guidelines suggested by the simulation results, we could find significant linear trend in the data of land air temperature and sea surface temperature.     

Feminized cultural capital at work in the moral economy: Home credit and working-class women

One of the defining features of the home credit sector is the role played by its agents—workers who act as intermediaries between lending companies and borrowers to facilitate lending and collect repayments. There is a prevailing and pervasive narrative in the sector that women make superior agents, largely based on the belief that female agents can manage relationships with borrowers more successfully than their male counterparts. This article analyzes data from 349,078 home credit accounts (loans), as well as 71 interviews with home credit agents and lending company managers, to evaluate both the myths and realities of women's roles in home credit. The data is also used to explore the opportunities for—and potential constraints on—women's career progression in home credit work, based on an understanding of the moral economy in which they operate. By exploring the moral economy of low-income communities, the article highlights the role of working-class women's cultural capital within the labor market. Despite women forming the majority of the agent workforce in home credit, women's capital is undervalued in comparison with their male counterparts' capital. The analysis within this article allows a greater understanding of the highly classed and gendered nature of the moral economy of low-income communities and the exchange value of women's capital within the labor market.