Objective Bayesian Testing of a Poisson Mean

We consider testing hypotheses about a single Poisson mean. When prior information is not available, use of objective priors is of interest. We provide intrinsic priors based on the arithmetic intrinsic and fractional Bayes factors, and evaluate their characteristics.     

AFTERWORD: CRITICAL INFORMATION STUDIES

This paper takes measure of an emerging scholarly field that sits at the intersection of many important areas of study. Critical Information Studies (CIS) considers the ways in which culture and information are regulated by their relationship to commerce, creativity, and other human affairs. CIS captures the variety of approaches and bodies of knowledge needed to make sense of important phenomena such as copyright policy, electronic voting, encryption, the state of libraries, the preservation of ancient cultural traditions, and markets for cultural production. It necessarily stretches to a wide array of scholarly subjects, employs multiple complementary methodologies, and influences conversations far beyond the gates of the university. Economists, sociologists, linguists, anthropologists, ethnomusicologists, communication scholars, lawyers, computer scientists, philosophers, and librarians have all contributed to this field, and thus it can serve as a model for how engaged, relevant scholarship might be carried out. CIS interrogates the structures, functions, habits, norms, and practices that guide global flows of information and cultural elements. Instead of being concerned merely with one's right to speak (or sing or publish), CIS asks questions about access, costs, and chilling effects on, within, and among audiences, citizens, emerging cultural creators, indigenous cultural groups, teachers, and students. Central to these issues is the idea of ‘semiotic democracy’, or the ability of citizens to employ the signs and symbols ubiquitous in their environments in manners that they determine.     

A new behavioural model for fertility schedules

Modelling age-specific fertility rates is of great importance in demography because of their influence on population growth. Although we have a variety of fertility models in the demographic literature, most of them do not have any demographic interpretation for their parameters. It is generally expected that models with behavioural interpretation are more universal than those without any interpretation. Even though the famous Gompertz model has some behavioural interpretation it suffers from other drawbacks. In the present work, we propose a new fertility model, which has its genesis in the generalization of logistic law. The proposed model has good behavioural interpretation, alongside having nice parameter interpretations.     

Investigating the Dynamics of Migration and Health in Australia: A Longitudinal Study

There have been few longitudinal studies investigating the immigrant health and changes in their health with longer residency in the host country. Additionally, the pathways and mechanisms by which transition of health over time occurs are poorly understood, limiting the ability to implement policies that will result in improved health for all, including immigrants. We assessed differences in health outcomes among foreign-born people from English speaking countries and non-English speaking countries relative to native-born Australians over a 10-year period using a large representative longitudinal dataset. We also explored English language proficiency, socio-economic factors and health behaviour factors as possible mechanisms through which health outcomes change over time post-migration. Conventional multilevel mixed and hybrid regression models were used to evaluate health outcomes in 9558 native-born and 3067 foreign-born people from the Household, Income and Labour Dynamics in Australia survey. There were clear differences in physical health, mental health and self-assessed health between foreign-born subgroups in comparison with native-born Australians. Foreign-born people from English speaking countries typically had a health advantage relative to native-born people, and foreign-born people from non-English speaking countries had a health disadvantage with respect to native-born people for all health outcomes. There was no evidence that these differences changed by duration of residence except for self-assessed health amongst foreign-born people from non-English speaking countries when duration of residence exceeded 20 years. English language proficiency mediated the relationship between duration of residence and health for foreign-born people from non-English speaking countries.     

Bounds on posterior expectations for density bounded class with constant bandwidth

We consider a certain (simplified) version of the density bounded class; see Lavine (J. Amer. Statist. Assoc. 86 (1991) 400–403). We find that this class has certain advantages over many other similar classes in terms of elicitation, ease of calculation and other characteristics of interest. Bounds on posterior expectations are considered. In particular, we show how certain bounds may be found in the (multidimensional) normal linear model problem.     

Selecting the precision parameter prior in Dirichlet process mixture models

We consider Dirichlet process mixture models in which the observed clusters in any particular dataset are not viewed as belonging to a finite set of possible clusters but rather as representatives of a latent structure in which objects belong to one of a potentially infinite number of clusters. As more information is revealed the number of inferred clusters is allowed to grow. The precision parameter of the Dirichlet process is a crucial parameter that controls the number of clusters. We develop a framework for the specification of the hyperparameters associated with the prior for the precision parameter that can be used both in the presence or absence of subjective prior information about the level of clustering. Our approach is illustrated in an analysis of clustering brands at the magazine Which?. The results are compared with the approach of Dorazio (2009) via a simulation study.     

Robust Bayesian analysis of the binomial empirical Bayes problem

Empirical Bayes estimation is considered for an i.i.d. sequence of binomial parameters θ_i arising from an unknown prior distribution G(.). This problem typically arises in industrial sampling, where samples from lots are routinely used to estimate the lot fraction defective of each lot. Two related issues are explored. The first concerns the fact that only the first few moments of G are typically estimable from the data. This suggests consideration of the interval of estimates (e.g., posterior means) corresponding to the different possible G with the specified moments. Such intervals can be obtained by application of well-known moment theory. The second development concerns the need to acknowledge the uncertainty in the estimation of the first few moments of G. Our proposal is to determine a credible set for the moments, and then find the range of estimates (e.g., posterior means) corresponding to the different possible G with moments in the credible set.     

一个时代的标志:数据拥抱户外广告

正数字户外广告的供应商,可以在天气寒冷时,播放咖啡广告;在炎热时,打出碳酸饮料广告;甚至还可以给广告牌编程,让它们在空气中满是花粉时,播放抗过敏药物的广告。户外广告业务是世界上最古老的营销形式之一,如今它正在拥抱数字技术。空置大多数形式的传统广告,比如印刷、广播、广播电视,多年来一直输给了在线广告。只有广告牌形式的户外广告(可追溯到19世纪)和电视广告一样,坚守了阵地。     

Sensitivity of some posterior summaries when the prior is unimodal with specified quantiles

Prior information is modeled either by (1) a class of unimodal distributions with specified quantiles, or by (2) an ∈-contamination class with contaminations subject to unimodal and quantile restrictions. We show how the ranges of certain posterior summaries can be found. Using numerical examples, we compare the robustness behaviour under these classes, and assess the effect, in terms of robustness, of specifying a base prior.