Sul ruolo dei riassunti esaustivi ai fini della previsione in contesto bayesiano (1a parte)

Si studia una nozione di riassunto esaustivo, che diremo a fini predittivi e che è già stata oggetto d'indagine da parte di F. Spizzichino sotto diversa denominazione. Si pone in evidenza la naturalezza di questa nuova definizione che, senza alcuna restrizione, può essere applicata in ogni tipo di ragionamento induttivo. Nella prima parte della ricerca, dopo alcune esemplificazioni sull'applicazione in alcuni tipici problemi inferenziali con particolare riguardo alla costruzione di modelli ipotetici a partire da considerazioni squisitamente predittive del concentto di riassunto esaustivo a fini predittivi, se ne studiano le principali proprietà. Nella seconda parte (che apparirà in un prossimo numero di questa Rivista) se ne analizzeranno i rapporti con le più abituali nozioni di riassunto esaustivo.

---

In this paper (first part of a wider work; the second part will appear in the next issue of this journal) we support the idea that the major objective of inductive reasoning is the distribution for outcomes of any sample not jet observed (predictive distribution) Parameters are a secondary device that can ultimately be justified and can lend some simplification.According to this point of view, we study a notion of prediction sufficiency introduced by F. Spizzichino (1978). Many of the results true for classical sufficient statistics apply to our predictive sufficient statistics as we demonstrate in Section 3.In the second part we analyse sequences of predictive sufficient statistics and their relations with classical sufficient statistics for the parameters which are limits of these sequences. The examples of Section 2 represent a first limited approach to this problem.

---

---

Lavoro eseguito nell'ambito del GNAFA-CNR.     

Modelling Determinants of Participation,Number of Trips and Site Choice for Outdoor Recreation in Protected Areas

This is a study on demand for outdoor recreation in a national system of environmentally protected areas. The exercise is based on a nationwide survey carried out in 1996 from a stratified random sample of 5,574 Italian households. Data on socio‐economic characteristics and recreational choice behaviour of respondents were collected and this information was supplemented by a second data‐base containing information on 193 Italian EPAs in order to characterise the different outdoor destinations on the basis of their recreational attributes. These data sets are used here to model choices of outdoor recreation within environmentally protected areas, using a sequence of three different models: (i) a dichotomous choice logit model for the probability of participation conditional on household covariates; (ii) a count data Poisson model to estimate the household's expected number of trips per year; (iii) a conditional logit model to estimate the probability of site selection conditional on site attributes. We report the estimated per‐trip welfare changes derivable from an actual policy proposal which would extend the area under environmental protection by ten per cent.     

Reforming regulation and supervision in Europe: Five missing lessons from the financial crisis

There is general agreement that financial regulation and supervision must be improved. But are the proposed reforms adequate to the task? What criteria should they fulfil in order to be effective?     

Understanding wage restraint in the German public sector: does the pattern bargaining hypothesis really hold water?

German public sector wage restraint has been explained through the presence of a specific type of inter-sectoral wage coordination in the industrial relations system—that is, export sector-led pattern bargaining. First, as a literature-assessing exercise, this paper reviews the literature in industrial relations and comparative political economy (CPE) and finds that (i) the origins and mechanics of inter-sectoral wage coordination through pattern bargaining have never been laid out clearly; (ii) that the mechanisms of the pattern bargaining thesis have never been tested empirically; and (iii) that the CPE literature reveals an export-sector bias. Second, as a theory-testing exercise, hoop tests are performed to verify the pattern bargaining hypothesis. The key finding is that Germany cannot be considered a case of export sector-driven pattern bargaining, opening a new research agenda for the study of public sector wage setting centred on public sector employment relations, public finance, public administrations and the politics of fiscal policy.     

Alternative econometric implementations of multi-factor models of the U.S. financial markets

This paper analyzes the empirical performance of two alternative ways in which multi-factor models with time-varying risk exposures and premia may be estimated. The first method echoes the seminal two-pass approach introduced by Fama and MacBeth (1973). The second approach is based on a Bayesian latent mixture model with breaks in risk exposures and idiosyncratic volatility. Our application to monthly, 1980–2010 U.S. data on stock, bond, and publicly traded real estate returns shows that the classical, two-stage approach that relies on a nonparametric, rolling window estimation of time-varying betas yields results that are unreasonable. There is evidence that most portfolios of stocks, bonds, and REITs have been grossly over-priced. On the contrary, the Bayesian approach yields sensible results and a few factor risk premia are precisely estimated with a plausible sign. Predictive log-likelihood scores indicate that discrete breaks in both risk exposures and variances are required to fit the data.     

Robots,Unions, and Aging: Determinants of Robot Adoption Evidence from OECD Countries

Atlantic Economic Journal -     

Designing a central bank: Social player,monetary agent,or banking agent?

This paper reviews recent advances on the role of the central bank in the money supply process and its effects on inflation. The literature is presented according to a three-stage process, with the central bank acting first as social player, then as monetary agent, and finally as a combined monetary and banking agent.     

Ownership as R&D incentive in business groups

Small and medium-sized enterprises (SMEs) are supposed to be less likely to conduct formal R&D because of the lack of financial resources, weaker competencies, and the absence of scale and scope economies. These limitations may be overcome when an SME belongs to a business group. Empirical studies have shown that firms belonging to business groups have a higher propensity to engage in R&D. We demonstrate that this higher propensity depends on the ownership of controlled companies, besides the presence of coordination mechanisms. We develop a model, and we empirically test its predictions using a data set of Italian SMEs operating in the manufacturing sector. From the model we derive three main implications: (1) there is no difference in R&D propensity between standalone firms and firms at the bottom of groups; (2) head and intermediate firms have a higher R&D propensity than standalone firms and firms at the bottom of the group; (3) the intensity of R&D depends on the ownership of controlled firms and on their size. Overall, the results of the empirical analysis are in accordance with the implications of the model.