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.     

Social Protection in the ‘Real World’: Issues,Models and Challenges

Social protection has evolved rapidly both conceptually and in practice, and is now a key policy issue in humanitarian and development debates. However, debates have sometimes been misled by approaches that pay inadequate attention to context‐specific factors, do not fully consider the sequence of interventions, and are too instrument‐centred. This article presents a conceptual framework to tailor social‐protection policy and implementation more closely to country contexts. Four stylised models of social protection are identified, corresponding to scenarios where social‐protection systems are absent, where elements of such systems exist, and where systems are emerging or have been consolidated. Each model is shown to lead to different challenges, implications and areas for further research.     

Similarities and Differences in Competitiveness Among European NUTS2 Regions: An Empirical Analysis Based on 2010–2013 Data

Social Indicators Research - Regional competitiveness is a concept whose definition and applicability is highly debated among scholars. Nevertheless, over recent years it has become widespread...     

Caloric restriction in trans

Caloric (or dietary) restriction (CR) is the most potent, robust, and reproducible known means of extending longevity and decreasing morbidity in laboratory mammals. Two of the major questions faced by researchers in this field are the applicability to humans and the biochemical mechanism(s) involved in the actions of CR. Studies in nonhuman primates are beginning to address the former; studies in phylogenetically lower organisms such as yeast and Drosophila are beginning to address the latter. de Cabo and colleagues now provide evidence that some aspects of CR can be reproduced in mammalian tissue culture cells exposed to sera from rats and monkeys subjected to CR. This work presents the initial development of a new model with which to approach mechanistic studies of CR and provides a new form of direct evidence that CR exerts at least some of its effects in trans.     

Assessing the ‘Choosiness’ of Job‐seekers. An Exploratory Approach and Evidence for Italy

Abstract. We use information about job search and work preferences, typically collected in a labour force survey, in order to construct an indicator of ‘choosiness’ of the labour supply of job‐seekers. The method for obtaining the indicator, first at individual level and then at aggregate levels, is based on results from multiple correspondence analysis. We investigate the informational value of the indicator by examining its stability over time and its predictive power on labour force transitions. Empirical analyses of cross‐section and panel samples of job‐seekers from the Italian quarterly Labour Force Survey clarify the potentials (and limitations) of the approach.     

Do more equal slices shrink the cake? An empirical investigation of tax-transfer reform proposals in Italy

A crucial issue in efficiency-equality evaluations of tax reforms resides in the possibility that the level as well as the distribution of welfare may change, where the household-specific measures of welfare capture the value of income as well as the value of leisure. A better-designed redistribution and income support system may not only foster equality but also improve the configuration of incentives and by this route contribute in its turn to efficiency. This paper presents an empirical analysis of the welfare effects for married couples of replacing the Italian tax system by three alternative hypothetical reforms: a flat tax, a negative income tax, and a work fare scheme. We employ a microeconometric model of household labour supply that represents partners simultaneous choices, allows for constraints in the choice of hours of work, and is sufficiently flexible to capture a large variety of supply responses. These features appear to be crucial in the evaluation of reform effects. The results suggest that there is scope for improving upon the current system under both the efficiency and the equality criterion. The benefits from the reforms, however, come from unexpected directions since the largest labour supply contribution come from poor and middle class households whereas rich households appear to be much less responsive to changes in the tax rates. The simulation results reveal that a crucial role in shaping the results is played by the relatively higher behavioural responsiveness of married women living in low and average income households.All correspondence to Ugo Colombino. We would like to thank Tom Wennemo for skilful programming assistance, Anne Skoglund for technical assistance and word processing, K.A. Breke and E. Holmøy and an anonymous referee for useful comments. Special thanks to Dino Rizzi (University of Venezia), who provided us with a program written by him for the simulation of the direct and inverse 1993 tax-transfer rules (Rizzi 1996). Part of the paper was written when Aaberge and Strøm were visiting ICER and the Department of Economics in Torino. ICER is gratefully acknowledged for providing financial support and excellent working conditions. Ugo Colombino gratefully acknowledges financial and organisational support from Statistics Norway and the Department of Economics in Oslo, and from the Italian Ministry of University and Scientific Research (MURST research grants 1998 and 2000). Responsible editor: Alessandro Cigno.     

Does business model affect accounting choices? An empirical analysis of European listed companies

Financial accounting research increasingly includes business model (BM) constructs, but the ability of financial reporting to capture BM characteristics has not been verified. This study empirically explores the links between BMs and accounting choices by clustering a sample of 103 European listed companies according to an innovative, nonlinear algorithm (self-organizing map) that uses pertinent industrial, strategic, governance, and financial variables to uncover different dimensions of a BM. The authors investigate accounting choices (accounting measurement, accounting treatment, and disclosure level) by companies that belong to the different identified BMs. The analysis of the relations between different company BMs and their accounting choices indicates no significant connections, which offers empirical confirmation of the criticisms regarding the inability of financial reporting to represent (or even consider) a company’s BM. The results suggest further attempt to capture BM in financial reporting, which requires regulators to establish accounting standards that acknowledge the value creation processes of an entity and incentivize managers to represent those processes.     

Beyond talk: Contributions of quantity and quality of communication to language success across socioeconomic strata

Infants from low-socioeconomic status (SES) households hear a projected 30 million fewer words than their higher-SES peers. In a recent study, Hirsh-Pasek et al. (Psychological Science, 2015; 26: 1071) found that in a low-income sample, fluency and connectedness in exchanges between caregivers and toddlers predicted child language a year later over and above quantity of talk (Hirsh-Pasek et al., Psychological Science, 2015; 26: 1071). Here, we expand upon this study by examining fluency and connectedness in two higher-SES samples. Using data from the NICHD Study of Early Child Care and Youth Development, we sampled 20 toddlers who had low, average, and high language outcomes at 36 months from each of 2 groups based on income-to-needs ratio (INR; middle and high) and applied new coding to the mother–toddler interaction at 24 months. In the high-INR group, the quality of mother–toddler interaction at 24 months accounted for more variability in language outcomes a year later than did quantity of talk, quality of talk, or sensitive parenting. These results could not be accounted for by child language ability at 24 months. These effects were not found in the middle-INR sample. Our findings suggest that when the quality of interaction, fluency and connectedness, predicts language outcomes, it is a robust relation, but it may not be universal.