Modeling Asymmetry of Information for a Sample of the Chilean Companies Using Deterministic and Stochastic Methodologies

In this research, a set of financial series with high frequency was modeled and forecasted using data from a sample of Chilean companies active in the capital market. We were worked with the series of Bid-Ask (Spread) as a measure of asymmetry of information. Both deterministic and stochastic methods of the sample of Chilean stock exchange were tested, for these purposes, we used intraday data equally spaced but with difference frequency from 2007 to 2013. The data included series belong to: service, energy, retail and mining companies. The deterministic forecasting methods used included Simple, Holt, Brown, and Damped Trend, and the stochastic forecast used were ARIMA (p, d, q), ARCH (p), GARCH (p, q), method. Besides were performed using functional curves including linear, logarithmic, inverse, quadratic, cubic, growth-exponential, and logistic. Each forecast result was compared using goodness of fit indices of the Root Mean Square Error, Mean Absolute Percentage Error and R-squared index. The methodology include two step, first we were calculated the forecast for each year of the study, and second, we were estimated the forecast for the total period of the sample. For the first result, the ARIMA (p, d, q) models provided an adequate forecast for 97% of the cases, and for the second result, the ARCH (p), GARCH (p, q) and ARIMA (p, d, q) models, provided an adequate forecast for 70%, 15% and 15% of the cases, respectively. The identification of models for each of the series, could provide knowledge about presence of possible imperfect information in the Chilean market.