Evaluating the existence of structural change in the brazilian term structure of interest: evidence based on cointegration models with structural break

This paper investigates whether there is evidence of structural change in the Brazilian term structure of interest rates. Multivariate cointegration techniques are used to verify this evidence. Two econometrics models are estimated. The rst one is a Vector Autoregressive Model with Error Correction Mechanism (VECM) with smooth transition in the deterministic coe¢ cients (Ripatti and Saikkonen [25]). The second one is a VECM with abrupt structural change formulated by Hansen [13]. Two datasets were analysed. The rst one contains a nominal interest rate with maturity up to three years. The second data set focuses on maturity up to one year. The rst data set focuses on a sample period from 1995 to 2010 and the second from 1998 to 2010. The frequency is monthly. The estimated models suggest the existence of structural change in the Brazilian term structure. It was possible to document the existence of multiple regimes using both techniques for both databases. The risk premium for di¤erent spreads varied considerably during the earliest period of both samples and seemed to converge to stable and lower values at the end of the sample period. Long-term risk premiums seemed to converge to inter-national standards, although the Brazilian term structure is still subject to liquidity problems for longer maturities.

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.

A comparison of test of non-linear cointegration with an application to the predictability of US interest rates using the term structure

We evaluate the forecasting performance of a number of systems models of US shortand long-term interest rates. Non-linearities, induding asymmetries in the adjustment to equilibrium, are shown to result in more accurate short horizon forecasts. We find that both long and short rates respond to disequilibria in the spread in certain circumstances, which would not be evident from linear representations or from single-equation analyses of the short-term interest rate.

Price discovery using a regime-sensitive cointegration approach

This work proposes a method to examine variations in the cointegration relation between preferred and common stocks in the Brazilian stock market via Markovian regime switches. It aims on contributing for future works in "pairs trading" and, more specifically, to price discovery, given that, conditional on the state, the system is assumed stationary. This implies there exists a (conditional) moving average representation from which measures of "information share" (IS) could be extracted. For identification purposes, the Markov error correction model is estimated within a Bayesian MCMC framework. Inference and capability of detecting regime changes are shown using a Montecarlo experiment. I also highlight the necessity of modeling financial effects of high frequency data for reliable inference.

Long term economic relationships from cointegration maps

We employ the Bayesian framework to define a cointegration measure aimed to represent long term relationships between time series. For visualization of these relationships we introduce a dissimilarity matrix and a map based on the sorting points into neighborhoods (SPIN) technique, which has been previously used to analyze large data sets from DNA arrays. We exemplify the technique in three data sets: US interest rates (USIR), monthly inflation rates and gross domestic product (GDP) growth rates. (c) 2007 Elsevier B.V. All rights reserved.

Cointegration: Bayesian Significance Test

To estimate causal relationships, time series econometricians must be aware of spurious correlation, a problem first mentioned by Yule (1926). To deal with this problem, one can work either with differenced series or multivariate models: VAR (VEC or VECM) models. These models usually include at least one cointegration relation. Although the Bayesian literature on VAR/VEC is quite advanced, Bauwens et al. (1999) highlighted that "the topic of selecting the cointegrating rank has not yet given very useful and convincing results". The present article applies the Full Bayesian Significance Test (FBST), especially designed to deal with sharp hypotheses, to cointegration rank selection tests in VECM time series models. It shows the FBST implementation using both simulated and available (in the literature) data sets. As illustration, standard non informative priors are used.

The Real Exchange Rate in Small Open Developed Economies: Evidence from Cointegration Analysis

We examine the effects of the terms of trade and the expected real interest rate differential on the real exchange rate in a sample of small open developed economies. We employ cointegration analysis to search for possible long-term linkages. We find that while both the terms of trade and the expected real interest rate differentials affect the real exchange rate in the long run, the role of the terms of trade generally proves more consistent across countries. The speed of adjustment for the expected real interest rate differential in the error-correction model, however, is quantitatively larger than it is for the terms of trade.

Nonstationary brand variables in category management: A cointegration perspective

Category-management models serve to assist in the development of plans for pricing and promotions of individual brands. Techniques to solve the models can have problems of accuracy and interpretability because they are susceptible to spurious regression problems due to nonstationary time-series data. Improperly stated nonstationary systems can reduce the accuracy of the forecasts and undermine the interpretation of the results. This is problematic because recent studies indicate that sales are often a nonstationary time-series. Newly developed correction techniques can account for nonstationarity by incorporating error-correction terms into the model when using a Bayesian Vector Error-Correction Model. The benefit of using such a technique is that shocks to control variates can be separated into permanent and temporary effects and allow cointegration of series for analysis purposes. Analysis of a brand data set indicates that this is important even at the brand level. Thus, additional information is generated that allows a decision maker to examine controllable variables in terms of whether they influence sales over a short or long duration. Only products that are nonstationary in sales volume can be manipulated for long-term profit gain, and promotions must be cointegrated with brand sales volume. The brand data set is used to explore the capabilities and interpretation of cointegration.

Stock market efficiency, the small firm effect and cointegration

The cointegration methodology commonly used for testing the efficiency of the foreign exchange market is applied to a sample of UK share prices. Specifically we test for static market efficiency in the share prices of small and large firms, using monthly data from January 1975 to December 1989. The empirical findings provide evidence of market efficiency for portfolios of large firms but of inefficiency for small firm portfolios. These results are indicative of a small firm effect in the UK stock market.

An econometric analysis of international tourism demand in Hong Kong : a cointegration and error correction approach

The purpose of this study is to develop econometric models to better understand the economic factors affecting inbound tourist flows from each of six origin countries that contribute to Hong Kong’s international tourism demand. To this end, we test alternative cointegration and error correction approaches to examine the economic determinants of tourist flows to Hong Kong, and to produce accurate econometric forecasts of inbound tourism demand. Our empirical findings show that permanent income is the most significant determinant of tourism demand in all models. The variables of own price, weighted substitute prices, trade volume, the share price index (as an indicator of changes in wealth in origin countries), and a dummy variable representing the Beijing incident (1989) are also found to be important determinants for some origin countries. The average long-run income and own price elasticity was measured at 2.66 and – 1.02, respectively. It was hypothesised that permanent income is a better explanatory variable of long-haul tourism demand than current income. A novel approach (grid search process) has been used to empirically derive the weights to be attached to the lagged income variable for estimating permanent income. The results indicate that permanent income, estimated with empirically determined relatively small weighting factors, was capable of producing better results than the current income variable in explaining long-haul tourism demand. This finding suggests that the use of current income in previous empirical tourism demand studies may have produced inaccurate results. The share price index, as a measure of wealth, was also found to be significant in two models. Studies of tourism demand rarely include wealth as an explanatory forecasting long-haul tourism demand. However, finding a satisfactory proxy for wealth common to different countries is problematic. This study indicates with the ECM (Error Correction Models) based on the Engle-Granger (1987) approach produce more accurate forecasts than ECM based on Pesaran and Shin (1998) and Johansen (1988, 1991, 1995) approaches for all of the long-haul markets and Japan. Overall, ECM produce better forecasts than the OLS, ARIMA and NAÏVE models, indicating the superiority of the application of a cointegration approach for tourism demand forecasting. The results show that permanent income is the most important explanatory variable for tourism demand from all countries but there are substantial variations between countries with the long-run elasticity ranging between 1.1 for the U.S. and 5.3 for U.K. Price is the next most important variable with the long-run elasticities ranging between -0.8 for Japan and -1.3 for Germany and short-run elasticities ranging between – 0.14 for Germany and -0.7 for Taiwan. The fastest growing market is Mainland China. The findings have implications for policies and strategies on investment, marketing promotion and pricing.

Is the Australian wool futures market efficient as a predictor of spot prices?

Giles and Goss (1980) have suggested that, if a futures market provides a forward pricing function, then it is an efficient market. In this article a simple test for whether the Australian Wool Futures market is efficient is proposed. The test is based on applying cointegration techniques to test the Law of One Price over a three, six, nine, and twelve month spread of futures prices. We found that the futures market is efficient for up to a six-month spread, but no further into the future. Because futures market prices can be used to predict spot prices up to six months in advance, woolgrowers can use the futures price to assess when they market their clip, but not for longer-term production planning decisions. (C) 1999 John Wiley & Sons, Inc.

Flex cars and the alcohol price

We build a model that incorporates the effect of the innovative ""flex"" car, an automobile that is able to run with either gasoline or alcohol, on the dynamics of fuel prices in Brazil. Our model shows that differences regarding fuel prices will now depend on the proportions of alcohol, gasoline and flex cars in the total stock. Conversely, the demand for each type of car will also depend on the expected future prices of alcohol and gasoline (in addition to the car prices). The model reflects our findings that energy prices are tied in the long run and that causality runs stronger from gasoline to alcohol. The estimated error correction parameter is stable, implying that the speed of adjustment towards equilibrium remains unchanged. The latter result is probably due to a still small fraction of flex cars in the total stock (approx. 5%), despite the fact that its sales nearly reached 100% in 2006. (C) 2009 Elsevier B.V. All rights reserved.

Bayesian analysis of the error correction model

This paper presents a method for estimating the posterior probability density of the cointegrating rank of a multivariate error correction model. A second contribution is the careful elicitation of the prior for the cointegrating vectors derived from a prior on the cointegrating space. This prior obtains naturally from treating the cointegrating space as the parameter of interest in inference and overcomes problems previously encountered in Bayesian cointegration analysis. Using this new prior and Laplace approximation, an estimator for the posterior probability of the rank is given. The approach performs well compared with information criteria in Monte Carlo experiments. (C) 2003 Elsevier B.V. All rights reserved.

A comparative study of alternative approaches for common factors identification

Preliminary version