Submitted by Vagner Enrico Castilho Alves (vagneralves@gmail.com) on 2014-08-26T17:29:47Z No. of bitstreams: 1 MPFE_Dissertacao_Vagner Enrico Castilho Alves_VF.pdf: 1506529 bytes, checksum: 5f1fd3e54f60edb8c87d8542948d2b57 (MD5) / Approved for entry into archive by JOANA MARTORINI (joana.martorini@fgv.br) on 2014-08-26T18:38:27Z (GMT) No. of bitstreams: 1 MPFE_Dissertacao_Vagner Enrico Castilho Alves_VF.pdf: 1506529 bytes, checksum: 5f1fd3e54f60edb8c87d8542948d2b57 (MD5) / Made available in DSpace on 2014-08-26T18:40:31Z (GMT). No. of bitstreams: 1 MPFE_Dissertacao_Vagner Enrico Castilho Alves_VF.pdf: 1506529 bytes, checksum: 5f1fd3e54f60edb8c87d8542948d2b57 (MD5) Previous issue date: 2014-08-08 / Este trabalho procurar analisar a validade da Paridade do Poder de Compra entre regiões metropolitanas do Brasil através do Índice de Preços do Consumidor Amplo (IPCA). Para isso foram realizados testes de raiz unitária para modelos lineares e não lineares, sobre cinco grupos do IPCA: Índice Geral, Administrados, Bens Comercializáveis, Bens Não Comercializáveis e Alimentos no Domicílio. O banco de dados utilizado compreende o período de 1991 a 2013 e os testes foram realizados sobre 550 séries, comparando-se todos os pares possíveis de regiões. Sob o modelo linear, não foi possível validar a PPC para a maioria das séries através do teste de raiz unitária DF-GLS, o que é diferente do esperado, uma vez que a análise intranacional elimina os efeitos da taxa de câmbio e reduz a influência dos custos de transações sobre as condições de arbitragem. Já o resultado do modelo não linear, realizado através do teste de Kapetanios, confirmou a estacionariedade de 203 séries, de tal forma que podemos afirmar que a PPC é válida para praticamente todos os pares possíveis de regiões metropolitanas abrangidas pelo IPCA nos cinco grupos estudados. Além disso, é possível observar que as séries apresentam maiores desvios entre os anos de 1991 e 1994, período marcado por grande instabilidade macroeconômica no Brasil e de sucessivos planos econômicos que não funcionaram. Após o início do plano real, em 1994, a relação da variação de preços entre regiões apresenta menor volatilidade e uma convergência mais rápida. / This paper analyses the validity of Purchasing Power Parity (PPP) between metropolitan regions of Brazil through the Consumer Price Index (IPCA). For this, we conducted unit root tests for linear and nonlinear models, on five groups of the IPCA: General Index, Regulated Prices, Tradable Goods, Non Tradable Goods and Food at Home. The database covers the period of 1991-2013 and the tests were conducted on 550 series, comparing all possible pairs of regions. On the linear model, it was not possible to validate the PPP for most of the series through the DF-GLS unit root test, which was not expected since the intra-national analysis should eliminate the effects of exchange rate and reduce the influence of transaction costs on arbitrage conditions. However, the result of the linear model, done through the Kapetanios test, confirmed the stationarity of 203 series, such that is possible to validate the PPP for almost all pairs of metropolitan areas covered by the IPCA in the five studied groups. Moreover, one can observe that the series have large deviations between the years of 1991 and 1994, a period marked by great macroeconomic instability in Brazil and successive economic plans that have not worked. After the beginning of the Real Plan in 1994, the ratio of the change in prices between regions stabilizes, presenting a low volatility and a short term convergence.

Submitted by Oscar Simoes (oscar.simoes@citi.com) on 2011-09-06T20:01:02Z No. of bitstreams: 1 Dissertação Oscar Simoes FINAL.pdf: 585897 bytes, checksum: 7cd8393ba1823e9dcfc4bde821b40736 (MD5) / Approved for entry into archive by Gisele Isaura Hannickel (gisele.hannickel@fgv.br) on 2011-09-08T12:46:40Z (GMT) No. of bitstreams: 1 Dissertação Oscar Simoes FINAL.pdf: 585897 bytes, checksum: 7cd8393ba1823e9dcfc4bde821b40736 (MD5) / Approved for entry into archive by Gisele Isaura Hannickel (gisele.hannickel@fgv.br) on 2011-09-08T12:48:10Z (GMT) No. of bitstreams: 1 Dissertação Oscar Simoes FINAL.pdf: 585897 bytes, checksum: 7cd8393ba1823e9dcfc4bde821b40736 (MD5) / Made available in DSpace on 2011-09-08T12:48:49Z (GMT). No. of bitstreams: 1 Dissertação Oscar Simoes FINAL.pdf: 585897 bytes, checksum: 7cd8393ba1823e9dcfc4bde821b40736 (MD5) Previous issue date: 2011-08-12 / Este trabalho tem três objetivos básicos, tendo como base um banco de dados de taxas reais de câmbio entre Brasil e 21 parceiros comerciais no período de 1957 a 2010. O primeiro objetivo é o de verificar a validade da Paridade do Poder de Compra entre Brasil e seus parceiros comerciais através de três testes de raiz unitária (ADF, PP, KPSS). Para a maioria dos países, os testes de raiz unitária foram inconclusivos ou não rejeitaram raiz unitária quando foram utilizados dados mensais e modelos lineares. Já para dados de periodicidade anual, houve maior aceitação de estacionariedade, além de um número menor de resultados inconclusivos. O segundo objetivo é o de investigar a hipótese em Taylor (2001) de que a meia-vida é superestimada quando a amostra é formada a partir de um processo de agregação temporal pela média. Os resultados confirmam as conclusões de Taylor e superestimam a meia-vida em uma janela de 35% a 56% do que seria a meia-vida calculada a partir de dados de final de período. O terceiro objetivo do trabalho é o de verificar se a taxa real de câmbio possui uma reversão não-linear à média. Considerando dados mensais, foi verificado que na maioria dos testes rejeita-se a hipótese nula de raiz unitária contra a hipótese alternativa de globalmente estacionária, porém não-linear. / This dissertation has three main objectives and is based on real exchange rates between Brazil and 21 commercial counterparties for the period of 1957-2010. The first objective is to verify the validity of the Purchasing Power Parity through 3 different linear unit root tests (ADF, PP, and KPSS). For the majority of the cases, null hypotheses of unit roots could not be rejected or were inconclusive for monthly end-of-period data and linear models. For yearly end-ofperiod data, results were more inclined to accepting stationarity, and the number of inconclusive results was reduced. The second objective is to investigate Taylor’s (2001) conclusion that temporal aggregation overestimates the half-lives of the real exchange rates. Under the tests done, Taylor’s points are confirmed, and half-lives are overestimated by a range of 35% to 56% when aggregated temporally by its means and when compared with endof-period half-lives. The third objective is to verify if real exchange rates have non-linear mean-reversion. Considering monthly data, the majority of the tests confirm non-linearity and global stationarity against the unit root hypothesis

Magister Scientiae - MSc / In recent years, two estimators have been proposed to correct the bias exhibited by the leastsquares (LS) estimator of the lagged dependent variable (LDV) coefficient in dynamic regression models when the sample is finite. They have been termed as ‘mean-unbiased’ and ‘medianunbiased’ estimators. Relative to other similar procedures in the literature, the two locationbased estimators have the advantage that they offer an exact and uniform methodology for LS estimation of the LDV coefficient in a first order autoregressive model with or without exogenous regressors i.e. ARX(1). However, no attempt has been made to accurately establish and/or compare the statistical properties among these estimators, or relative to those of the LS estimator when the LDV coefficient is restricted to realistic values. Neither has there been an attempt to  compare their performance in terms of their mean squared error (MSE) when various forms of the exogenous regressors are considered. Furthermore, only implicit confidence intervals have been given for the ‘medianunbiased’ estimator. Explicit confidence bounds that are directly usable for inference are not available for either estimator. In this study a new estimator of the LDV coefficient is proposed; the ‘most-probably-unbiased’ estimator. Its performance properties vis-a-vis the existing estimators are determined and compared when the parameter space of the LDV coefficient is restricted. In addition, the following new results are established: (1) an explicit computable form for the density of the LS estimator is derived for the first time and an efficient method for its numerical evaluation is proposed; (2) the exact bias, mean, median and mode of the distribution of the LS estimator are determined in three specifications of the ARX(1) model; (3) the exact variance and MSE of LS estimator is determined; (4) the standard error associated with the determination of same quantities when simulation rather than numerical integration method is used are established and the methods are compared in terms of computational time and effort; (5) an exact method of evaluating the density of the three estimators is described; (6) their exact bias, mean, variance and MSE are determined and analysed; and finally, (7) a method of obtaining the explicit exact confidence intervals from the distribution functions of the estimators is proposed. The discussion and results show that the estimators are still biased in the usual sense: ‘in expectation’. However the bias is substantially reduced compared to that of the LS estimator. The findings are important in the specification of time-series regression models, point and interval estimation, decision theory, and simulation. / South Africa

本研究目的在於探討投資等級債券信用價差是否存在外溢效果。信用價差是建構各種信用衍生性金融商品的基礎，惟目前學術界及業界都著眼在信用價差的拆解。信用價差可拆解成預期違約損失、稅的溢酬及信用風險溢酬。投資等級債券的信用價差來自於預期違約損失、稅的溢酬的部分較少，絕大多數來自於信用風險溢酬。信用風險溢酬係系統性影響信用價差的因素，此因素造成不同投資等級債券的信用價差間具有共整合的現象，進而引發外溢效果。然而並無人對於信用價差外溢效果作一深入探討。本研究利用目前學術界盛行的Panel模型的研究方法，對各種投資等級的債券的信用價差進行Panel Unit Root Tests、Panel Cointegration Tests及Panel Spillover Effect Tests，以求發現債券信用價差外溢效果存在與否的證據。 本文以iBoxx Index成份債券作為研究標的，利用Panel研究方法得到以下結論: 1.根據研究結果顯示，各種信評等級的債券的信用價差存在單根問題。 2.不同投資等級信評債券的信用價差擁有共整合關係。 3.不同投資等級信用評等的債券間信用價差外溢效果存在。且愈是相 鄰信評等級債券的外溢效果愈為顯著，例如BBB等級信用價差發生變動引發信評AAA等級信用價差變動的幅度便沒有AA等級信用價差變動引發AAA等級信用價差變動來得強烈。外溢效果係不對稱，當最高投資等級信評發生變動時，最低投資等級債券變動最為激烈;而最低投資等級信評發生波動時，最高投資等級債券發生變動的幅度就較小。 4.本研究支持不同債信評等的債券存在同向的外溢效果。 / This paper investigates the spillover effect in the investment grade bonds using the recently developed Panel Unit Root Tests, Panel Cointegrations Tests, Panel FMOLS and Panel DOLS techniques. Investment grade bonds’ credit spreads are found to be nonstationary and to be cointegrated in panels. This paper finds evidence of spillover effects.