On-line expectation–maximization algorithm for latent data models

Summary.  We propose a generic on-line (also sometimes called adaptive or recursive) version of the expectation–maximization (EM) algorithm applicable to latent variable models of independent observations. Compared with the algorithm of Titterington, this approach is more directly connected to the usual EM algorithm and does not rely on integration with respect to the complete-data distribution. The resulting algorithm is usually simpler and is shown to achieve convergence to the stationary points of the Kullback–Leibler divergence between the marginal distribution of the observation and the model distribution at the optimal rate, i.e. that of the maximum likelihood estimator. In addition, the approach proposed is also suitable for conditional (or regression) models, as illustrated in the case of the mixture of linear regressions model.     

武当道茶文化研究

This article explores the promotion of tea culture at Wudang Mountain, a Daoist tem-ple complex in Hubei Province that is a popular tourist destination. At shops in temples and market areas, vendors brand their tea as Wudang Daoist tea, emphasizing its health benefits and connecting their teas to the Daoist discourse of life-nourishing ( yang sheng) practices. In their marketing materi-als and on their websites, the management of the Eight Immortal Temple Tea Plantation further cites folklore and mythic history to claim profound local roots for Wudang tea culture. In so doing, this company echoes the memory narratives of more fa-mous Chinese teas like Iron Guanyin and Dahong-pao. In China as elsewhere, convenient travel now puts people in contact with areas and peoples that a few decades earlier only a few non-locals explored. As a consequence of a global trend towards com-modification, members of local groups, including distinctive ethnocultural groups, now seek to create distinctive local brands for a tourist market. Corpo-rations now regularly mine local traditions to find i-tems that they can transform into commodities for a wider market ( Comaroff and Comaroff 2009 ) . One of Hubei’s richest tourism assets is the Daoist temple complex at Wudang Moutain, which draws pilgrims and tourists from China and Greater China. China’s State Council identified Wudang Moutain as a National Key Scenic Area in 1982 , and UNESCO added its ancient temples to its World Heritage list in 1994 . The Chinese govern-ment has worked with the Daoist Federation to de-velop Wudang’s temples and pavilions, which are spread over 400 square kilometers of mountainous terrain, into a major tourist destination. The gov-ernment tourist office promotes Wudang Mountain for its scenic beauty, its deep historical heritage, its religious culture, and famous martial arts. Al-though its tea culture is less renowned, local tea sellers claim that Wudang tea has a deep history and Daoist qualities. At Wudang Mountain, the Eight Immortal Temple Tea Plantation markets their tea as Wudang Daoist Tea, using history, legend, ritual, and sa-cred location to distinguish its green, black, and oolong teas from those produced elsewhere. They seek to valorize their teas through claims about the excellence of their growing environment ( not un-like the terroir of a fine wine ) and the historical depth of their tea history. They further use legend and mythic history to position their products, and associate their teas with Daoist traditions of health preservation, including martial arts. Finally, they use modern marketing techniques to promote their teas, including a promotional video directed by a In Ethnicity Inc, John and Jean Comaroff pro-pose that “commerce has been instrumental either in crystallizing or in reproducing the sociological entities (‘people’, ‘nation’, ‘community’ ) in which cultural identity is presumed to inhere”( Comaroff and Comaroff 2009:114 ) . In particu-lar, they conclude that people use identity-laden objects as a vehicle through which “ethnic con-sciousness is materialized” ( 33 ) . They focus on the modern discourse of intellectual property rights, including competing national claims to trademark signature products (122). Wudang tea vendors have used story, packa-ging, and performance to promote teas that evoke Wudang’s history, local traditions, and landscape. Hubei officials pay premium prices for the Eight Immortal Temple Plantation’s highest quality teas, but outside China Wudang tea is not well known. As global awareness of this world heritage site grows, Hubei’s Wudang Daoist tea series may find a place among the specialty teas now sold on the world market. But for now, Wudang Daoist Tea is an innovative brand that symbolizes a heritage that is simultaneously imperial, national, Daoist, and deeply local.     

Eight Motivational Forces and Voluntary Turnover: A Theoretical Synthesis with Implications for Research

In this study, we synthesize, from the attitude and turnover literatures, a framework of eight (8) distinctive motives, or “Forces”. We then illustrate how the “8 Forces” framework can be utilized by turnover researchers as clarification of reported reasons for turnover, as causal mediators of turnover predictors, and as factors related to the type of turnover decision process. Finally, we discuss further implications of this framework.     

The Fairness of Decision Rules

Prior work on resource allocation has generally considered only a small number of allocation rules, usually reflecting equity or equality. We use a scenario study to examine the effect of eight different allocation rules (past performance, future performance, rank, random draw, chance meetings, business need, personal need, and political reasons) on recipient reactions to the gain or loss of three different kinds of resources in an organizational setting. We find evidence that allocations based on past performance and random draw rules lead to the highest fairness perceptions and the lowest expectations that the decisions made will lead to intragroup conflict. However, fairness judgments are also influenced by a variety of other factors, such as the type of resource being allocated and whether the recipient is advantaged or disadvantaged relative to others in the workgroup (what we term the “egocentric interaction”). We discuss how our results might influence managers’ allocation decisions.     

Grey Advantage: New strategies for the old

With nearly one fifth of the population of the industrialized world soon to be beyond a traditional retirement age, businesses need to re-appraise their attitudes towards both older workers and older customers. Whilst some public and private sector organizations may have signalled such intentions, the gap between the rhetoric and reality of ‘third age’ employment and grey market development is still substantial. Analysing the ‘Age-Quake’, this article reviews current ageing population trends and associated business agendas. Using case study analysis, it then challenges three perceived ‘grey discontinuities’, as well as the traditional perception of simplistic step-change declines in physical and mental abilities and economic activity at the traditional retirement age. Deriving from this, the article challenges the older received wisdom by offering the individual assessment of ‘third-agers’ in terms of abilities as employees and tastes as customers as two generic strategies to assist managers in the strategic alignment of their organizations in pursuit of “grey advantage”.     

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.     

Relative effect sizes for measures of risk

Effect sizes are an important component of experimental design, data analysis, and interpretation of statistical results. In some situations, an effect size of clinical or practical importance may be unknown to the researcher. In other situations, the researcher may be interested in comparing observed effect sizes to known standards to quantify clinical importance. In these cases, the notion of relative effect sizes (small, medium, large) can be useful as benchmarks. Although there is generally an extensive literature on relative effect sizes for continuous data, little of this research has focused on relative effect sizes for measures of risk that are common in epidemiological or biomedical studies. The aim of this paper, therefore, is to extend existing relative effect sizes to the relative risk, odds ratio, hazard ratio, rate ratio, and Mantel–Haenszel odds ratio for related samples. In most scenarios with equal group allocation, effect sizes of 1.22, 1.86, and 3.00 can be taken as small, medium, and large, respectively. The odds ratio for a non rare event is a notable exception and modified relative effect sizes are 1.32, 2.38, and 4.70 in that situation.     

Simplified Likelihood Based Goodness-of-fit Tests for the Weibull Distribution

The aim of this paper is to present new likelihood based goodness-of-fit tests for the two-parameter Weibull distribution. These tests consist in nesting the Weibull distribution in three-parameter generalized Weibull families and testing the value of the third parameter by using the Wald, score, and likelihood ratio procedures. We simplify the usual likelihood based tests by getting rid of the nuisance parameters, using three estimation methods. The proposed tests are not asymptotic. A comprehensive comparison study is presented. Among a large range of possible GOF tests, the best ones are identified. The results depend strongly on the shape of the underlying hazard rate.