Resumo

Forecasting the future behavior of asset prices based on historical market data has been a popular and important subject for academic research and practitioners. In particular, technical analysts, or chartists, believe that past stock prices and trading volume may show patterns that indicate future trends. In particular, daily high and low prices provide valuable information regarding the dynamic process of an asset throughout time. These prices can be seen as references values for investors in order to place buy or sell orders, e.g. through candlestick charts, a popular technical indicator.

The aim of this work is to contribute to previous literature on technical analysis and also to market practitioners by evaluating a trading strategy based on high and low stock prices forecasts using data from equity shares negotiated at the BM\&FBOVESPA. Based on an empirical analysis, the research goal is to answer the following questions: i) are high and low prices of equity shares traded at the BM\&FBOVESPA predictable?; ii) which approach is appropriate to model these prices?; iii) can high and low prices forecasts produce profitable results using TA trading strategies?

Although many research has been devoted to the analysis of the predictability of daily market closing prices, few studies based on econometric time series models examined the case of high and low prices, as for instance the works of Baruník and Dvoráková (2015) and Caporin et al. (2013). Also, the literature presented substancial evidence of long memory in the volatility process of asset prices, interest rate differentials, inflation rates, forward premiums and exchange rates, but few of them studied the range volatility dynamics.

This work provides an empirical study on the modeling and predictability of daily high and low prices from the ten of the most widely traded stocks at the BM&FBOVESPA over the period from January 2010 to May 2017. It is suggested a fractionally cointegrated vector autoregressive model (FCVAR), formalized by Johansen and Nielsen (2012), to model the relationship between highs and lows. Finally, it is suggested a simple trading strategy based on daily high and low FCVAR forecasts. The results are then compared against traditional benchmarks over different prediction horizons.

The findings indicated that daily high and low prices are integrated of an order close to the unity, and the range displays long memory and is in the stationary region. The empirical FCVAR model shows that high and low prices move in opposite directions to restore equilibrium after a shock to the system occurs. Also, the results evidence the predictability of daily highs and lows in the Brazilian stock market for different forecasting horizons, in which the fractionally approach conducts to better predictions than competitive methods and can improve trading strategies.

This paper addressed the modeling and forecasting of daily high and low asset prices in the Brazilian stock market using a FCVAR model. Empirical findings indicate a significant cointegration relationship between daily high and low prices. Based on historical data, results support that high and low prices of equity shares are largely predictable and their forecasts can improve TA trading strategies applied on Brazilian stock prices. Further, the fractionally cointegrated approach appears as a potential forecasting tool for market practitioners, improving investment strategies.

BARUNÍK, J.; DVORÁKOVÁ, S. An empirical model of fractionally cointegrated daily high and low stock market prices. Economic Modelling, v. 45, pp. 193-206, 2015. CAPORIN, M.; RANALDO, A.; MAGISTRIS, P. C. On the predictability of stock prices: A case for high and low prices. Journal of Banking & Finance, v. 37, pp. 5132-5146, 2013. JOHANSEN, S.; NIELSEN, M. O. Likelihood inference for a fractionally cointegrated vector autoregressive model. Econometrica, v. 80, n. 6, pp. 2667-2732, 2012.