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.     

Effects of long-acting testosterone undecanoate on bone mineral density in middle-aged men with late-onset hypogonadism and metabolic syndrome: results from a 36 months controlled study

We evaluated the effects of long-term testosterone replacement therapy (TRT) on the bone mineral density (BMD) in obese patients with metabolic syndrome (MS) and late-onset hypogonadism (LOH). Sixty men (mean age 57 ± 10) with low serum testosterone (T < 320 ng/dL) and MS regardless the presence of osteoporosis were enrolled. Forty men received intramuscular T-undecanoate (TU) four times/year for 36 months and 20 age-matched hypogonadal men with MS in whom T treatment was contraindicated were used as controls. Hormonal, biochemical markers, vertebral and femoral BMD by dual-energy x-ray absorptiometry were measured. At baseline, overall patients had mild osteopenia (lumbar BMD= 0.891 ± 0.097 g/cm(2); femoral BMD= 0.847 ± 0.117 g/cm(2)). TU induced a significant improvement of bone mass after 36 months (lumbar BMD=1.053 ± 0.145 g/cm(2); p < 0.002; femoral BMD=0.989 ± 0.109; p < 0.003 g/cm(2)) with a 5%/year increase and a significant reduction in hs-CRP without changes in body mass index. A direct relationship between serum T and BMD increments at the lumbar (r(2)?= 0.66, p < 0.0001) and femoral (r(2)?=0.52, p < 0.0001) sites was demonstrated. Study adherence was 50% without serious side effects. Long-term TRT in middle-aged men with LOH and MS determines a significant increase in both vertebral and femoral BMD related to increased serum T levels, probably independently from estradiol modifications.     

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 -     

REPLY TO ULMER: Symbolic Interactionism or A Structural Alternative?

In his critique of our 1999 article "Desensitizing Herbert Blumer's Work on Race Relations: Recent Applications of His Group Position Theory to the Study of Contemporary Race Prejudice,' Jeffery Ulmer charges us with providing a "questionable' interpretation of Blumer's ideas on the grounds that we (1) neglect (or distort) Blumer's advocation for making abstract generalizations in the form of "definitive' concepts, and thus sabotage Blumer's empirical methodology as well as that of symbolic interactionism in general and (2) fail to address a body of literature that deals with "repackaging' Blumer's ideas in such a way that "solves' the sorts of tensions we raise between Blumer's theory and quantitative research. Ulmer fears that our representation of Blumer and symbolic interactionism may result in a host of "mythic facts' (a term borrowed from David Maines) that will undermine Blumer's contributions "to a viable and whole science of the social, including race relations."     

Book reviews

Brezzi Francesca, A Partire dal Gioco ‐ Per i Sentieri di un Pensiero Ludico Marinetti, Genova, 1992, pp. 134, L. 25.000

Ian McIntyre, DOGFIGHT ‐ The Transatlantic Battle over Airbus, Praeger Publishers, 112 pages, $42

Angela Ales Bello, Fenomenología dell'essere umano. Lineamenti di una filosofía al femminile, Roma, Città Nuova, 1992, pp. 170 L. 18.000

“A Critical Note on Some Literature Concerning Backwardness and Social Unbalances in Islamic Countries”     

A model for estimating point sources in spatial data

We introduce a point source model which may be useful for estimating point sources in spatial data. It may also be useful for modelling general spatial data, and providing a simple explanatory model for some data, whilst in other cases it may give a parsimonious representation. The model assumes that there are point sources (or sinks), usually at unknown positions, and that the mean value at a site depends on the distance from these sources. We discuss the general form of the model, and some methods for estimating the sources and the regression parameters. We demonstrate the methodology using a simulation study, and apply the model to two real data sets. Some possibilities for further research are outlined.     

Neurocognitive Effects in Welders Exposed to Aluminium: An Application of the NPC Test and NPC Ranking Methods

The aim of this study is to investigate the effects of exposure to aluminium on the cognitive sphere in a group of welders. Given the intrinsic complexity of the neurocognitive sphere, three different psychomotor variables were used for its investigation allowing the resulting problem to be naturally modelized into a multivariate framework and solved by a nonparametric combination of permutation tests (NPC test). In order to make the treated and control groups comparable, we also stratified the samples on the basis of a risk index that estimates the combined action of biological age and exposure time. Despite the fact that studies in the literature have reached conflicting results, our study highlights a significant drop in attention and memory performances in individuals exposed to aluminium. Finally, we identify a global criterion that summarises the information on the neurocognitive state by applying the nonparametric combination of dependent rankings method (NPC ranking).     

INTERTEMPORAL CHOICE AND CONSUMPTION MOBILITY

The theory of intertemporal consumption choice makes sharp predictions about the evolution of the entire distribution of household consumption, not just about its conditional mean. In the paper, we study the empirical transition matrix of consumption using a panel drawn from the Bank of Italy Survey of Household Income and Wealth. We estimate the parameters that minimize the distance between the empirical and the theoretical transition matrix of the consumption distribution. The transition matrix generated by our estimates matches remarkably well the empirical matrix, both in the aggregate and in samples stratified by education. Our estimates strongly reject the consumption insurance model and suggest that households smooth income shocks to a lesser extent than implied by the permanent income hypothesis. (JEL: D52, D91, I30)     

A measure of interrater absolute agreement for ordinal categorical data

Statistical Methods & Applications - A measure of interrater absolute agreement for ordinal scales is proposed capitalizing on the dispersion index for ordinal variables proposed by Giuseppe...