We study model selection strategies based on penalized empirical loss minimization. We point out a tight relationship between error estimation and data-based complexity penalization: any good error estimate may be converted into a data-based penalty function and the performance of the estimate...

This paper studies the determination of the surpluses of the Brazilian central government. For quarterly data from 1996 through 2011, the empirical strategy included: i) structural break models and nonlinear estimates on the level of public debt, to handle the inertia after 1999, for high levels...

Estimates based on household surveys often differ considerably from administrative records. In the PNADs, for instance, the estimated number of beneficiaries of the Programa Bolsa Família (PBF) and of the Benefício de Prestação Continuada (BPC) are always lower than the official figures....

The Brazilian municipalities show a huge disparity in income level. The GDP per capita difference between the richest and the poorest municipalities is about 190 times, according to IBGE (2000) database. Institutionalist theory provides a plausible explanation for the gap among municipalities...

The technological and institutional environment influences the way of doing research and the relationships between its participants. Intellectual property is a strategic issue to build the institutional framework of the new technological regime and therefore the dynamics of innovation in...

In this work we consider modeling the past volatilities through a Generalized Autoregressive Conditional Heteroskedasticity (GARCH) model using the Bayesian approach. Asymmetries in the shocks are accommodated by smooth transition models for the variance. We discuss problems related to the...

This article brings new inputs to debate outsourcing in Brazil, using a new methodology based on administrative records. With this methodology, it is possible to identify 4.02 million outsourced workers, corresponding to 11.7% of total employees in the urban private sector. Moreover, with this...