A class of improved heteroskedasticity-consistent covariance matrix estimators

The heteroskedasticity-consistent covariance matrix estimator proposed by White (1980), also known as HC0, is commonly used in practical applications and is implemented into a number of statistical software. Cribari–Neto, Ferrari & Cordeiro (2000) have developed a bias-adjustment scheme that delivers bias-corrected White estimators. There are several variants of the original White estimator that also commonly used by practitioners. These include the HC1, HC2 and HC3 estimators, which have proven to have superior small-sample behavior relative to White’s estimator. This paper defines a general bias-correction mechamism that can be applied not only to White’s estimator, but to variants of this estimator as well, such as HC1, HC2 and HC3. Numerical evidence on the usefulness of the proposed corrections is also presented. Overall, the results favor the sequence of improved HC2 estimators.

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).

Volatility Triggered Range Forward (VTRF): an instrument for protection against volatility fluctuations in the BRL/USD pair

Este trabalho propõe um instrumento capaz de absorver choques no par BRL/USD, garantindo ao seu detentor a possibilidade de realizar a conversão entre essas moedas a uma taxa observada recentemente. O Volatility Triggered Range Forward assemelha-se a um instrumento forward comum, cujo preço de entrega não é conhecido inicialmente, mas definido no momento em que um nível de volatilidade pré-determinado for atingido na cotação das moedas ao longo da vida do instrumento. Seu cronograma de ajustes pode ser definido para um número qualquer de períodos. Seu apreçamento e controle de riscos é baseado em uma árvore trinomial ponderada entre dois possíveis regimes de volatilidade. Esses regimes são determinados após um estudo na série BRL/USD no período entre 2003 e 2009, basedo em um modelo Switching Autoregressive Conditional Heteroskedasticity (SWARCH).

A Common-feature approach for testing present-value restrictions with financial data

It is well known that cointegration between the level of two variables (labeled Yt and yt in this paper) is a necessary condition to assess the empirical validity of a present-value model (PV and PVM, respectively, hereafter) linking them. The work on cointegration has been so prevalent that it is often overlooked that another necessary condition for the PVM to hold is that the forecast error entailed by the model is orthogonal to the past. The basis of this result is the use of rational expectations in forecasting future values of variables in the PVM. If this condition fails, the present-value equation will not be valid, since it will contain an additional term capturing the (non-zero) conditional expected value of future error terms. Our article has a few novel contributions, but two stand out. First, in testing for PVMs, we advise to split the restrictions implied by PV relationships into orthogonality conditions (or reduced rank restrictions) before additional tests on the value of parameters. We show that PV relationships entail a weak-form common feature relationship as in Hecq, Palm, and Urbain (2006) and in Athanasopoulos, Guillén, Issler and Vahid (2011) and also a polynomial serial-correlation common feature relationship as in Cubadda and Hecq (2001), which represent restrictions on dynamic models which allow several tests for the existence of PV relationships to be used. Because these relationships occur mostly with nancial data, we propose tests based on generalized method of moment (GMM) estimates, where it is straightforward to propose robust tests in the presence of heteroskedasticity. We also propose a robust Wald test developed to investigate the presence of reduced rank models. Their performance is evaluated in a Monte-Carlo exercise. Second, in the context of asset pricing, we propose applying a permanent-transitory (PT) decomposition based on Beveridge and Nelson (1981), which focus on extracting the long-run component of asset prices, a key concept in modern nancial theory as discussed in Alvarez and Jermann (2005), Hansen and Scheinkman (2009), and Nieuwerburgh, Lustig, Verdelhan (2010). Here again we can exploit the results developed in the common cycle literature to easily extract permament and transitory components under both long and also short-run restrictions. The techniques discussed herein are applied to long span annual data on long- and short-term interest rates and on price and dividend for the U.S. economy. In both applications we do not reject the existence of a common cyclical feature vector linking these two series. Extracting the long-run component shows the usefulness of our approach and highlights the presence of asset-pricing bubbles.

Mudanças de regime e persistência dos choques sobre a volatilidade para a série de preços do petróleo: uma análise comparativa da família GARCH e modelos com mudança de regime Markoviana – MSIH e SWARCH

A previsão dos preços do petróleo é fundamental para o planejamento energético e oferece subsídio a tomada de decisões de longo prazo, que envolvem custos irrecuperáveis. No entanto, os preços do petróleo são muito instáveis sujeitos a choques como resultado de questões geopolíticas, poder de mercado da OPEP (Organização dos Países Exportadores de Petróleo) e pressões de demanda resultando numa série sujeita a quebras estruturais, prejudicando a estimação e previsão de modelos de série temporal. Dada a limitação dos modelos de volatilidade da família GARCH, que são instáveis e apresentam elevada persistência em séries com mudanças estruturais, este trabalho compara a previsão da volatilidade, em termos de intervalos de confiança e persistência, dos modelos de volatilidade com mudança de regime markoviana em relação aos modelos de volatilidade determinísticos. Os modelos de volatilidade com mudança de regime considerados são o modelo SWARCH (Markov Switch ARCH) e introduz-se o modelo MSIH (Markov Switch Intercept Heteroskedasticity) para o estudo da volatilidade. Como resultado as previsões de volatilidade dos modelos com mudança de regime permitem uma estimação da volatilidade que reduz substancialmente a persistência em relação aos modelos GARCH.

US real interest rates and default risk in emerging economies

This paper empirically investigates the impact of changes in US real interest rates on sovereign default risk in emerging economies using the method of identification through heteroskedasticity. Policy-induced increases in US interest rates starkly raise default risk in emerging market economies. However, the overall correlation between US real interest rates and the risk of default is negative, demonstrating that the effects of other variables dominate the anterior relationship

O impacto das intervenções do Banco Central Brasileiro no mercado cambial: uma análise de efetividade sobre a volatilidade

Desde a adoção do sistema de câmbio flutuante pelo Banco Central do Brasil, tanto a autoridade monetária quanto o governo brasileiro têm instituído medidas convencionais e não convencionais de intervenção no mercado de câmbio. Dentre essas medidas, salientam-se as compras e vendas de dólares no mercado de spot e derivativos, cujas finalidades precípuas seriam a tentativa de estabilizar os mercados em situação de “stress” e suavizar uma determinada tendência de valorização ou desvalorização da moeda brasileira. O presente trabalho analisa os efeitos de referidas intervenções sobre a volatilidade na moeda brasileira. Utilizamos modelos econométricos da família ARCH (Autoregressive Conditional Heteroskedasticity) com o intuito de se averiguar o efeito sobre a volatilidade de curto e longo prazo, inclusive com metodologias semelhantes às empregadas em trabalhos direcionados a outras economias emergentes. Com o propósito de se estudar o efeito sinalizador das intervenções, foram utilizadas regressões simples com dados de volatilidade implícita e risk reversal do mercado de opções do dólar/real. Concluiu-se pela não relevância dos efeitos das intervenções sobre o nível da taxa de câmbio. No que concerne às volatilidades de curto e longo prazo, verificou-se que as vendas de dólares aumentam ambas as volatilidades, porém, quanto às compras, estas não apresentaram significância. No que se refere aos efeitos sinalizadores, via volatilidade implícita e risk reversal, estes também não expuseram relevância. Enfim, o que talvez possa consistir em fundamento para a não relevância dessas intervenções é o fato de o Brasil se consubstanciar em uma economia emergente e com menor credibilidade na condução de suas políticas monetárias.

Modelos de previsão de volatilidade : uma aplicação do modelo GARCH a taxas de câmbio

Com o objetivo de mostrar uma aplicação dos modelos da família GARCH a taxas de câmbio, foram utilizadas técnicas estatísticas englobando análise multivariada de componentes principais e análise de séries temporais com modelagem de média e variância (volatilidade), primeiro e segundo momentos respectivamente. A utilização de análise de componentes principais auxilia na redução da dimensão dos dados levando a estimação de um menor número de modelos, sem contudo perder informação do conjunto original desses dados. Já o uso dos modelos GARCH justifica-se pela presença de heterocedasticidade na variância dos retornos das séries de taxas de câmbio. Com base nos modelos estimados foram simuladas novas séries diárias, via método de Monte Carlo (MC), as quais serviram de base para a estimativa de intervalos de confiança para cenários futuros de taxas de câmbio. Para a aplicação proposta foram selecionadas taxas de câmbio com maior market share de acordo com estudo do BIS, divulgado a cada três anos.

Theoretical and empirical essays on microeconometrics

This Master Thesis consists of one theoretical article and one empirical article on the field of Microeconometrics. The first chapter\footnote{We also thank useful suggestions by Marinho Bertanha, Gabriel Cepaluni, Brigham Frandsen, Dalia Ghanem, Ricardo Masini, Marcela Mello, Áureo de Paula, Cristine Pinto, Edson Severnini and seminar participants at São Paulo School of Economics, the California Econometrics Conference 2015 and the 37\textsuperscript{th} Brazilian Meeting of Econometrics.}, called \emph{Synthetic Control Estimator: A Generalized Inference Procedure and Confidence Sets}, contributes to the literature about inference techniques of the Synthetic Control Method. This methodology was proposed to answer questions involving counterfactuals when only one treated unit and a few control units are observed. Although this method was applied in many empirical works, the formal theory behind its inference procedure is still an open question. In order to fulfill this lacuna, we make clear the sufficient hypotheses that guarantee the adequacy of Fisher's Exact Hypothesis Testing Procedure for panel data, allowing us to test any \emph{sharp null hypothesis} and, consequently, to propose a new way to estimate Confidence Sets for the Synthetic Control Estimator by inverting a test statistic, the first confidence set when we have access only to finite sample, aggregate level data whose cross-sectional dimension may be larger than its time dimension. Moreover, we analyze the size and the power of the proposed test with a Monte Carlo experiment and find that test statistics that use the synthetic control method outperforms test statistics commonly used in the evaluation literature. We also extend our framework for the cases when we observe more than one outcome of interest (simultaneous hypothesis testing) or more than one treated unit (pooled intervention effect) and when heteroskedasticity is present. The second chapter, called \emph{Free Economic Area of Manaus: An Impact Evaluation using the Synthetic Control Method}, is an empirical article. We apply the synthetic control method for Brazilian city-level data during the 20\textsuperscript{th} Century in order to evaluate the economic impact of the Free Economic Area of Manaus (FEAM). We find that this enterprise zone had positive significant effects on Real GDP per capita and Services Total Production per capita, but it also had negative significant effects on Agriculture Total Production per capita. Our results suggest that this subsidy policy achieve its goal of promoting regional economic growth, even though it may have provoked mis-allocation of resources among economic sectors.

Monetary policy, default risk and the exchange rate

In a country with high probability of default, higher interest rates may render the currency less attractive if sovereign default is costly. This paper develops that intuition in a simple model and estimates the effect of changes in interest rates on the exchange rate in Brazil using data from the dates surrounding the monetary policy committee meetings and the methodology of identification through heteroskedasticity. Indeed, we find that unexpected increases in interest rates tend to lead the Brazilian currency to depreciate. It follows that granting more independence to a central bank that focus solely on inflation is not always a free-lunch.