On identifiability of parametric statistical models

Summary This is a review article on statistical identifiability. Besides the definition of the main concepts, we deal with several questions relevant to the statistician: parallelism between parametric identifiability and sample sufficiency; relationship of identifiability with measures of sample information and with the inferential concept of estimability; several strategies of making inferences in unidentifiable models with emphasis on the distinct behaviour of the classical and Bayesian approaches. The concepts, ideas and methods discussed are illustrated with simple examples of statistical models. Centro de Análise e Processamento de Sinais da UTL     

Trust in leadership: A multi-level review and integration

Leaders have been argued to play a key role in determining organizational effectiveness across all levels (e.g., individual, team, unit) that exist within organizations. A key component in a leader's ability to be effective within such environments is the degree to which subordinates and co-workers trust him/her. Therefore, it is not surprising that researchers and practitioners alike are interested in identifying the mechanisms through which trust in leadership can be developed as well as those factors which moderate this relationship [e.g., Gillespie, N. A., Mann, L. (2004). Transformational leadership and shared values: The building blocks of trust. Journal of Managerial Psychology, 19, 588–607; Kouzes and Posner, 1995; Roberts, K. H., O'Reilly, C. A. (1974). Failures in upward communication in organizations: Three possible culprits. Academy of Management Journal, 17, 205–215; Whitener, E. M. (1997). The impact of human resource activities on employee trust. Human Resource Management Review, 7, 389–404]. Despite this, research that has addressed the factors that foster trust in leaders and the outcomes of this trust has been disjointed and, as yet, no comprehensive model has been presented to systematically examine these factors. Therefore, the purpose of this article will be to present an integrative model of trust in leadership.     

Strategic management in a firm of consulting engineers

This article describes the introduction of strategic management in a large and diversified company of consulting engineers in Brazil. This was done by a massive strategic planning effort in which the 60 top people of the company actively participated. This approach was chosen to produce both a comprehensive corporate strategy and strategic management capability throughout the company. The project therefore gave as much attention to training and guidance as to planning itself. Psychological, organizational and ‘political’ factors were taken seriously into account. Project management was a good joint-venture between some top people inside and some external consultants, strongly interacting with each other. The project resulted not only in plans, but also in decisions, including tidying-up the divisional structure of the firm. The article evaluates the project to determine success factors in such undertakings. It is interesting for managers to appreciate the factors involved in efforts to produce plans, develop managers and reorient a company at the same time. It is also interesting because it shows a fruitful, although demanding role for management consultants in strategic reorientations: more committed, more ‘on-line’ than experts submitting recommendations; less amorphous and more performance-oriented than organizational development gurus.     

Certifiable Pre‐Play Communication: Full Disclosure

This article asks when communication with certifiable information leads to complete information revelation. We consider Bayesian games augmented by a pre‐play communication phase in which announcements are made publicly. We first characterize the augmented games in which there exists a fully revealing sequential equilibrium with extremal beliefs (i.e., any deviation is attributed to a single type of the deviator). Next, we define a class of games for which existence of a fully revealing equilibrium is equivalent to a richness property of the evidence structure. This characterization enables us to provide different sets of sufficient conditions for full information disclosure that encompass and extend all known results in the literature, and are easily applicable. We use these conditions to obtain new insights in games with strategic complementarities, voting with deliberation, and persuasion games with multidimensional types.     

From reform to crisis: Argentina's pension system

Argentina underwent economic and social collapse in December 2001. The crisis brought the worst socioeconomic indicators in its history, and the pension system was not immune from this disaster, which was unparalleled in any middle-income developing country. In 1994 the pension system had been restructured, and was regarded as a viable model for other reforms elsewhere. This article discusses in general terms the features of the current pension scheme, the structural problems that were not resolved in the reform of 1994, the relation between that reform and the government's financial crisis, and the impact of the economic collapse on the pension system. Finally, it discusses some aspects of the challenges faced in building a system that is financially viable and has the potential to close the major gaps in coverage affecting both the working population and older persons.     

Mitigating the political participation gap from the school: the roles of civic knowledge and classroom climate

Empirical evidence has consistently shown that political participation is positively related with socioeconomic background. Furthermore, recent research suggests that children who come from low status families are already less willing to get politically involved. The present paper aims to analyze the possible impact that schools can have in mitigating the effect of parents' socioeconomic status on students' expected electoral participation, focusing on two variables: civic knowledge and classroom climate. The analyses are based on a series of multilevel models using Chilean data of the International Civic and Citizenship Education Study 2009. The results support the influence of students' socioeconomic background on expected electoral participation. Furthermore, civic knowledge and classroom climate show a positive and similar influence on students' expected participation. However, classroom climate appears less affected by students' background than civic knowledge, opening the discussion about which strategy should be emphasized when aiming to mitigate the political participation gap.     

Joint regression modeling for missing categorical covariates in generalized linear models

Missing covariates data is a common issue in generalized linear models (GLMs). A model-based procedure arising from properly specifying joint models for both the partially observed covariates and the corresponding missing indicator variables represents a sound and flexible methodology, which lends itself to maximum likelihood estimation as the likelihood function is available in computable form. In this paper, a novel model-based methodology is proposed for the regression analysis of GLMs when the partially observed covariates are categorical. Pair-copula constructions are used as graphical tools in order to facilitate the specification of the high-dimensional probability distributions of the underlying missingness components. The model parameters are estimated by maximizing the weighted log-likelihood function by using an EM algorithm. In order to compare the performance of the proposed methodology with other well-established approaches, which include complete-cases and multiple imputation, several simulation experiments of Binomial, Poisson and Normal regressions are carried out under both missing at random and non-missing at random mechanisms scenarios. The methods are illustrated by modeling data from a stage III melanoma clinical trial. The results show that the methodology is rather robust and flexible, representing a competitive alternative to traditional techniques.     

The expected impact of the 2019 Brazilian pension reform on survivors’ pensions

This study analyses the expected changes in survivors’ pensions resulting from the permanent rules of the 2019 pension reform in Brazil. Actuarial annuities are used for representative worker profiles. The dispersion in the replacement rate values decreases, except for the highest income level. The rates needed to finance survivors’ pensions decrease relatively more than do the rates for old-age pensions. The internal rates of return significantly decrease. There is a heterogeneous change in the distributive aspects of the pension system. The reform shall affect the adequacy and intragenerational equity of old-age and survivors’ pensions.     

Explaining Investment Dynamics in U.S. Manufacturing: A Generalized (S,s) Approach

In this paper we derive a model of aggregate investment that builds from the lumpy microeconomic behavior of firms facing stochastic fixed adjustment costs. Instead of the standard sharp (S,s) bands, firms' adjustment policies take the form of a probability of adjustment (adjustment hazard) that responds smoothly to changes in firms' capacity gap. The model has appealing aggregation properties, and yields nonlinear aggregate time series processes. The passivity of normal times is, occasionally, more than offset by the brisk response to large accumulated shocks. Using within and out-of-sample criteria, we find that the model performs substantially better than the standard linear models of investment for postwar sectoral U.S. manufacturing equipment and structures investment data.