On Bayesian learning from Bernoulli observations

We provide a reason for Bayesian updating, in the Bernoulli case, even when it is assumed that observations are independent and identically distributed with a fixed but unknown parameter _θ0${\theta }_0$. The motivation relies on the use of loss functions and asymptotics. Such a justification is important due to the recent interest and focus on Bayesian consistency which indeed assumes that the observations are independent and identically distributed rather than being conditionally independent with joint distribution depending on the choice of prior.     

ANOTHER STEP IN THE STUDY OF RACE RELATIONS

Recent qualitative researchers have argued the need for a more sensitizing approach to race research that elevates in importance the concerns and interests of those under study. This article illustrates how Herbert Blumer's work on race relations, critical race theory, and participatory action research may help this objective. These projects' similar epistemologies advance a type of social imagery that has powerful emancipatory implications in regard to racial oppression. Simply put, dominant renditions of social reality–including structural imperatives and racial identities–are illustrated to be socially constructed and hence open to negotiation. As a result of this shift, sensitizing methodologies (e.g., storytelling and collaboration) are employed that allow minorities an opportunity for self-representation. The liberating potential of all these projects can be further enhanced by relating their conceptual links to recent developments in contemporary social theory. Specifically, the typical concerns with process, interaction, and experiential meanings are intersubjectively mediated and not reducible to an objective subjective theoretical framework. Rather than simply personal or external, all knowledge is recognized to be fluid and coproduced. By grounding research on this intersubjective region, equitable exchanges are possible.     

Spatial hidden Markov models and species distributions

A spatial hidden Markov model (SHMM) is introduced to analyse the distribution of a species on an atlas, taking into account that false observations and false non-detections of the species can occur during the survey, blurring the true map of presence and absence of the species. The reconstruction of the true map is tackled as the restoration of a degraded pixel image, where the true map is an autologistic model, hidden behind the observed map, whose normalizing constant is efficiently computed by simulating an auxiliary map. The distribution of the species is explained under the Bayesian paradigm and Markov chain Monte Carlo (MCMC) algorithms are developed. We are interested in the spatial distribution of the bird species Greywing Francolin in the south of Africa. Many climatic and land-use explanatory variables are also available: they are included in the SHMM and a subset of them is selected by the mutation operators within the MCMC algorithm.     

CUSTOMER OWNERSHIP AND QUALITY PROVISION IN PUBLIC SERVICES UNDER ASYMMETRIC INFORMATION

The implementation of projects producing external effects is often a source of disagreement and conflict between hosting and nonhosting communities. The article focuses on the impact of participatory ownership on conflict resolution and social welfare in the presence of asymmetric information and imperfect quality monitoring. We show that in such situations the participatory solution may help solve deadlocks that money transfers to a for‐profit operator cannot solve. The analysis highlights three main factors behind this fact. First, a customer‐owned cooperative internalizes, at least partially, the external effects generated by the project. Second, the alignment of cooperative members' preferences with those of the social planner reduces (in some cases eliminates) the distortions caused by information asymmetries. Third, cooperatives require less costly monitoring than their for‐profit counterparts. We also show that cooperatives' productive inefficiency with respect to for‐profits may emerge endogenously as a consequence of a lower pressure to compete on costs for the market. (JEL H23, L33, P13)     

FDR- and FWE-controlling methods using data-driven weights

Weighted methods are an important feature of multiplicity control methods. The weights must usually be chosen a priori, on the basis of experimental hypotheses. Under some conditions, however, they can be chosen making use of information from the data (therefore a posteriori) while maintaining multiplicity control. In this paper we provide: (1) a review of weighted methods for familywise type I error rate (FWE) (both parametric and nonparametric) and false discovery rate (FDR) control; (2) a review of data-driven weighted methods for FWE control; (3) a new proposal for weighted FDR control (data-driven weights) under independence among variables; (4) under any type of dependence; (5) a simulation study that assesses the performance of procedure of point 4 under various conditions.     

Statistical matching and uncertainty analysis in combining household income and expenditure data

Among the goals of statistical matching, a very important one is the estimation of the joint distribution of variables not jointly observed in a sample survey but separately available from independent sample surveys. The absence of joint information on the variables of interest leads to uncertainty about the data generating model since the available sample information is unable to discriminate among a set of plausible joint distributions. In the present paper a short review of the concept of uncertainty in statistical matching under logical constraints, as well as how to measure uncertainty for continuous variables is presented. The notion of matching error is related to an appropriate measure of uncertainty and a criterion of selecting matching variables by choosing the variables minimizing such an uncertainty measure is introduced. Finally, a method to choose a plausible joint distribution for the variables of interest via iterative proportional fitting algorithm is described. The proposed methodology is then applied to household income and expenditure data when extra sample information regarding the average propensity to consume is available. This leads to a reconstructed complete dataset where each record includes measures on income and expenditure.     

Bayesian Inference and Forecasting in Dynamic Neural Networks with Fully Markov Switching ARCH Noises

We deal with one-layer feed-forward neural network for the Bayesian analysis of nonlinear time series. Noises are modeled nonlinearly and nonnormally, by means of ARCH models whose parameters are all dependent on a hidden Markov chain. Parameter estimation is performed by sampling from the posterior distribution via Evolutionary Monte Carlo algorithm, in which two new crossover operators have been introduced. Unknown parameters of the model also include the missing values which can occur within the observed series, so, considering future values as missing, it is also possible to compute point and interval multi-step-ahead predictions.     

Inference from PseudoLikelihoods with Plug‐In Estimates

Effective implementation of likelihood inference in models for high‐dimensional data often requires a simplified treatment of nuisance parameters, with these having to be replaced by handy estimates. In addition, the likelihood function may have been simplified by means of a partial specification of the model, as is the case when composite likelihood is used. In such circumstances tests and confidence regions for the parameter of interest may be constructed using Wald type and score type statistics, defined so as to account for nuisance parameter estimation or partial specification of the likelihood. In this paper a general analytical expression for the required asymptotic covariance matrices is derived, and suggestions for obtaining Monte Carlo approximations are presented. The same matrices are involved in a rescaling adjustment of the log likelihood ratio type statistic that we propose. This adjustment restores the usual chi‐squared asymptotic distribution, which is generally invalid after the simplifications considered. The practical implication is that, for a wide variety of likelihoods and nuisance parameter estimates, confidence regions for the parameters of interest are readily computable from the rescaled log likelihood ratio type statistic as well as from the Wald type and score type statistics. Two examples, a measurement error model with full likelihood and a spatial correlation model with pairwise likelihood, illustrate and compare the procedures. Wald type and score type statistics may give rise to confidence regions with unsatisfactory shape in small and moderate samples. In addition to having satisfactory shape, regions based on the rescaled log likelihood ratio type statistic show empirical coverage in reasonable agreement with nominal confidence levels.     

Erratum to: Crime Patterns between Tradition and Change: A Territorial Analysis of the Italian Provinces

Social Indicators Research -