Optimal two-sided tests for instrumental variables regression with heteroskedastic and autocorrelated errors

This paper considers two-sided tests for the parameter of an endogenous variable in an instrumental variable (IV) model with heteroskedastic and autocorrelated errors. We develop the nite-sample theory of weighted-average power (WAP) tests with normal errors and a known long-run variance. We introduce two weights which are invariant to orthogonal transformations of the instruments; e.g., changing the order in which the instruments appear. While tests using the MM1 weight can be severely biased, optimal tests based on the MM2 weight are naturally two-sided when errors are homoskedastic. We propose two boundary conditions that yield two-sided tests whether errors are homoskedastic or not. The locally unbiased (LU) condition is related to the power around the null hypothesis and is a weaker requirement than unbiasedness. The strongly unbiased (SU) condition is more restrictive than LU, but the associated WAP tests are easier to implement. Several tests are SU in nite samples or asymptotically, including tests robust to weak IV (such as the Anderson-Rubin, score, conditional quasi-likelihood ratio, and I. Andrews' (2015) PI-CLC tests) and two-sided tests which are optimal when the sample size is large and instruments are strong. We refer to the WAP-SU tests based on our weights as MM1-SU and MM2-SU tests. Dropping the restrictive assumptions of normality and known variance, the theory is shown to remain valid at the cost of asymptotic approximations. The MM2-SU test is optimal under the strong IV asymptotics, and outperforms other existing tests under the weak IV asymptotics.

Pair trading in Bovespa with a quantitative approach: cointegration, Ornstein-Uhlenbeck equation and Kelly criterion.

Pair trading is an old and well-known technique among traders. In this paper, we discuss an important element not commonly debated in Brazil: the cointegration between pairs, which would guarantee the spread stability. We run the Dickey-Fuller test to check cointegration, and then compare the results with non-cointegrated pairs. We found that the Sharpe ratio of cointegrated pairs is greater than the non-cointegrated. We also use the Ornstein-Uhlenbeck equation in order to calculate the half-life of the pairs. Again, this improves their performance. Last, we use the leverage suggested by Kelly Formula, once again improving the results.

Súmula vinculante e ratio decidendi : uma abordagem empírica a respeito de redesenho institucional e cultura jurídica

A Reforma do Judiciário de 2004 é parte de um longo processo de tentativas políticas de implementação de mudanças que não surgiriam espontaneamente na cultura jurídica. A súmula vinculante é exemplar desse histórico, pois se trata de instrumento voltado para corrigir problemas persistentes que decorrem da ausência de uma cultura jurídica de precedentes no Brasil. Entretanto, o próprio funcionamento do instituto depende da adequada aplicação da lógica de precedentes, pois a clareza dos enunciados vinculantes aprovados decorre da clareza da ratio decidendi de seus respectivos precedentes. Além do estudo dos debates legislativos que criaram o instituto da súmula vinculante, bem como dos procedimentos de aprovação das súmulas vinculantes penais editadas até o final de 2010, pesquisou-se como o Supremo Tribunal Federal administrou o manejo deste instituto conflitante com a maneira tradicional de fundamentação judicial e de referência não-fática, mas conceitual, entre decisões passadas.

Is there a general criterion for dynamic efficiency?

This paper analyses an overlapping generations model with absolute bequest motive. It is shown that the widely accepted criterion to verify dynamic efficiency does not apply to this case. In our model the social planner maximizes welfare by choosing a capital stock larger than the golden role and a real rate of interest smaller than the rate of growth of the economy.

A conditional likelihood ratio test for structural models

This paper develops a general method for constructing similar tests based on the conditional distribution of nonpivotal statistics in a simultaneous equations model with normal errors and known reducedform covariance matrix. The test based on the likelihood ratio statistic is particularly simple and has good power properties. When identification is strong, the power curve of this conditional likelihood ratio test is essentially equal to the power envelope for similar tests. Monte Carlo simulations also suggest that this test dominates the Anderson- Rubin test and the score test. Dropping the restrictive assumption of disturbances normally distributed with known covariance matrix, approximate conditional tests are found that behave well in small samples even when identification is weak.

Debt management in Brazil: evaluation of the Real Plan and challenges ahead

The Brazilian domestic debt has posed two challenges to policy-makers: it has grown very fast and its maturity is extremely short. This has prompted fears that a default or a compulsory lengthening scheme would be imposed. Here, we analyse the domestic public debt management experience in Brazil, searching for policy prescriptions for the next few years. After briefiy reviewing the recent domestic public debt history, we decompose the large rise in federal bonded debt during 1995-2000, searching for its macroeconomic causes. The main culprits are the extremely high interest payments-which, unti11998, were caused by the weak fiscal stance and the quasi-fixed exchange-rate regime; and since 1999, by the impact ofthe currency depreciation On the dollar-indexed and the externai debt-, and the accumulation of assets of doubtful value, much of which may have to be written off in the future. Simulation exercises of the net debt path for the near future underscore the importance of a tighter fiscal stance to prevent the debt-GDP ratio from growing further. Given the need to quickly lengthen the debt maturity, our main policy advice is to foster, and rely more on, infiation-linked bonds.

Consumption-wealth ratio and expected stock returns: evidence from panel data

This paper investigates the role of consumption-wealth ratio on predicting future stock returns through a panel approach. We follow the theoretical framework proposed by Lettau and Ludvigson (2001), in which a model derived from a nonlinear consumer’s budget constraint is used to settle the link between consumption-wealth ratio and stock returns. Using G7’s quarterly aggregate and financial data ranging from the first quarter of 1981 to the first quarter of 2014, we set an unbalanced panel that we use for both estimating the parameters of the cointegrating residual from the shared trend among consumption, asset wealth and labor income, cay, and performing in and out-of-sample forecasting regressions. Due to the panel structure, we propose different methodologies of estimating cay and making forecasts from the one applied by Lettau and Ludvigson (2001). The results indicate that cay is in fact a strong and robust predictor of future stock return at intermediate and long horizons, but presents a poor performance on predicting one or two-quarter-ahead stock returns.

Consumption-Wealth Ratio and Expected Stock Returns: Evidence from Panel Data on G7 Countries

Using the theoretical framework of Lettau and Ludvigson (2001), we perform an empirical investigation on how widespread is the predictability of cay {a modi ed consumption-wealth ratio { once we consider a set of important countries from a global perspective. We chose to work with the set of G7 countries, which represent more than 64% of net global wealth and 46% of global GDP at market exchange rates. We evaluate the forecasting performance of cay using a panel-data approach, since applying cointegration and other time-series techniques is now standard practice in the panel-data literature. Hence, we generalize Lettau and Ludvigson's tests for a panel of important countries. We employ macroeconomic and nancial quarterly data for the group of G7 countries, forming an unbalanced panel. For most countries, data is available from the early 1990s until 2014Q1, but for the U.S. economy it is available from 1981Q1 through 2014Q1. Results of an exhaustive empirical investigation are overwhelmingly in favor of the predictive power of cay in forecasting future stock returns and excess returns.

Brazil’s 35 years-old quasi-stagnation: facts and theory

Brazil is growing around 1% per capita a year from 1981; this means for a country that is supposed to catch up, quasi-stagnation. Four historical new facts explain why growth was so low after the Real Plan: the reduction of public savings, and three facts that reduce private investments: the end of the unlimited supply of labor, a very high interest rate, and the 1990 dismantling of the mechanism that neutralized the Dutch disease, which represented a major competitive disadvantage for the manufacturing industry. New-developmental theory offers an explanation and two solutions for the problem, but does not underestimate the political economy problems involved

Quasi-experimental estimates of fiscal spillovers and spatial interactions among Brazilian cities

Nós usamos a metodologia de Regressões em Descontinuidade (RDD) para estimar o efeito causal do Fundo de Participação dos Municípios (FPM) recebido por um município sobre características dos municípios vizinhos, considerando uma variedade de temas: finanças públicas, educação, saúde e resultados eleitorais. Nós exploramos a regra que gera uma variação exógena da transferência em munícipios próximos às descontinuidades no repasse do fundo de acordo com faixas de população. Nossa principal contribuição é estimar separadamente e em conjunto o efeito spillover e o efeito direto do FPM, considerando ambos municípios vizinhos ou apenas um deles próximos às mudanças de faixa. Dessa forma, conseguimos entender melhor a interação entre municípios vizinhos quando há uma correlação na probabilidade de receber uma transferência federal. Nós mostramos que a estimativa do efeito direto do FPM sobre os gastos locais diminui em cerca de 20% quando controlamos pelo spillover do vizinho, que em geral é positivo, com exceção dos gastos em saúde e saneamento. Nós estimamos um efeito positivo da transferência sobre notas na prova Brasil e taxas de aprovação escolares em municípios vizinhos e na rede estadual do ensino fundamental. Por outro lado, o recebimento de FPM por municípios vizinhos de pequena população reduz o provimento de bens e serviços de saúde em cidades próximas e maiores, o que pode ocorrer devido à redução da demanda por serviços de saúde. A piora de alguns indicadores globais de saúde é um indício, no entanto, de que podem existir problemas de coordenação para os prefeitos reterem seus gastos em saúde. De fato, quando controlamos pela margem de vitória nas eleições municipais e consideramos apenas cidades vizinhas com prefeitos de partido diferentes, o efeito spillover é maior em magnitude, o que indica que incentivos políticos são importantes para explicar a subprovisão de serviços em saúde, por um lado, e o aumento da provisão de bens em educação, por outro. Nós também constatamos um efeito positivo do FPM sobre votos para o partido do governo federal nas eleições municipais e nacionais, e grande parte desse efeito é explicado pelo spillover do FPM de cidades vizinhas, mostrando que cidades com dependência econômica do governo federal se tornam a base de sustentação e apoio político desse governo. Por fim, nós encontramos um efeito ambíguo do aumento de receita devido ao FPM sobre a competição eleitoral nas eleições municipais, com uma queda da margem de vitória do primeiro colocado e uma redução do número de candidatos, o que pode ser explicado pelo aumento do custo fixo das campanhas locais.