Desenvolvimento de metodologia de rating baseada no modelo ordered probit

Nos últimos anos o mercado de crédito brasileiro apresentou grande crescimento em termos de volume e modalidade de operações de crédito. Além disso, observou-se também o aumento da participação dos bancos nesse setor, principais intermediários financeiros da economia. Com isso, em um mercado em desenvolvimento, torna-se cada vez mais importante a correta avaliação e administração do risco financeiro envolvido nas operações: o risco de crédito. Nesse contexto, a classificação de rating surge como referência para investidores. No entanto, como o mercado bancário brasileiro ainda é pouco desenvolvido, apenas instituições de grande porte são classificados pelas agências de rating em funcionamento no país. Este trabalho tem como objetivo o desenvolvimento de uma metodologia de rating baseada no modelo ordered probit, que seja capaz de replicar o nível de rating de uma determinada agência, e assim conseguir estimar o nível de rating para aqueles bancos que não têm a referida classificação de rating

Intellectual property and competition as complementary policies: a test using an ordered probit model

Este Artigo Testa a Proposição da Teoria Econômica de que Propriedade Intelectual e Defesa da Concorrência são Políticas Complementares. um Modelo Probit Ordenado é Utilizado para Estimar os Efeitos Marginais do Uso e Qualidade do Enforcement dos Direitos de Propriedade Intelectual em uma Medida da Gravidade dos Problemas Relacionados À Concorrência. os Resultados Obtidos Reforçam a Noção de que as Políticas de Concorrência e Propriedade Intelectual não são Contraditórias.

Formation and destruction of coalition groups under economic growth

This paper introduces a model economy in which formation of coalition groups under technological progress is generated endogenously. The coalition formation depends crucially on the rate of arrival of new technologies. In the model, an agent working in the saroe technology for more than one period acquires skills, part of which is specific to this technology. These skills increase the agent productivity. In this case, if he has worked more than one period with the same technology he has incentives to construct a coalition to block the adoption of new technologies. Therefore, in every sector the workers have incentives to construct a coalition and to block the adoption of new technologies. They will block every time that a technology stay in use for more than one period.

Inference in differences-in-differences with few treated groups and heteroskedasticity

Differences-in-Differences (DID) is one of the most widely used identification strategies in applied economics. However, how to draw inferences in DID models when there are few treated groups remains an open question. We show that the usual inference methods used in DID models might not perform well when there are few treated groups and errors are heteroskedastic. In particular, we show that when there is variation in the number of observations per group, inference methods designed to work when there are few treated groups tend to (under-) over-reject the null hypothesis when the treated groups are (large) small relative to the control groups. This happens because larger groups tend to have lower variance, generating heteroskedasticity in the group x time aggregate DID model. We provide evidence from Monte Carlo simulations and from placebo DID regressions with the American Community Survey (ACS) and the Current Population Survey (CPS) datasets to show that this problem is relevant even in datasets with large numbers of observations per group. We then derive an alternative inference method that provides accurate hypothesis testing in situations where there are few treated groups (or even just one) and many control groups in the presence of heteroskedasticity. Our method assumes that we can model the heteroskedasticity of a linear combination of the errors. We show that this assumption can be satisfied without imposing strong assumptions on the errors in common DID applications. With many pre-treatment periods, we show that this assumption can be relaxed. Instead, we provide an alternative inference method that relies on strict stationarity and ergodicity of the time series. Finally, we consider two recent alternatives to DID when there are many pre-treatment periods. We extend our inference methods to linear factor models when there are few treated groups. We also derive conditions under which a permutation test for the synthetic control estimator proposed by Abadie et al. (2010) is robust to heteroskedasticity and propose a modification on the test statistic that provided a better heteroskedasticity correction in our simulations.

Inference in differences-in-differences with few treated groups and heteroskedasticity

Differences-in-Differences (DID) is one of the most widely used identification strategies in applied economics. However, how to draw inferences in DID models when there are few treated groups remains an open question. We show that the usual inference methods used in DID models might not perform well when there are few treated groups and errors are heteroskedastic. In particular, we show that when there is variation in the number of observations per group, inference methods designed to work when there are few treated groups tend to (under-) over-reject the null hypothesis when the treated groups are (large) small relative to the control groups. This happens because larger groups tend to have lower variance, generating heteroskedasticity in the group x time aggregate DID model. We provide evidence from Monte Carlo simulations and from placebo DID regressions with the American Community Survey (ACS) and the Current Population Survey (CPS) datasets to show that this problem is relevant even in datasets with large numbers of observations per group. We then derive an alternative inference method that provides accurate hypothesis testing in situations where there are few treated groups (or even just one) and many control groups in the presence of heteroskedasticity. Our method assumes that we know how the heteroskedasticity is generated, which is the case when it is generated by variation in the number of observations per group. With many pre-treatment periods, we show that this assumption can be relaxed. Instead, we provide an alternative application of our method that relies on assumptions about stationarity and convergence of the moments of the time series. Finally, we consider two recent alternatives to DID when there are many pre-treatment groups. We extend our inference method to linear factor models when there are few treated groups. We also propose a permutation test for the synthetic control estimator that provided a better heteroskedasticity correction in our simulations than the test suggested by Abadie et al. (2010).