The stocks that were studied were the NYSE and TSX. The dependence of one
stock market on the other was also studied and how much of a factor it plays in forecasting the
next price. Weather data was also studied. The three weather variables studied were the daily
averages of pressure,wind speed and temperature for the Ottawa region. Multiple forecast
densities were built and compared to see which method has the highest accuracy. It was found
that when dealing with non-linear data, the one-step method is more efficient in estimating the
true conditional density. The two-step approach is
better when trying to estimate a univariate
conditional density. When trying to estimate multivariate conditional density the further one
goes away from stationarity, the better that the 2-step method is. Real
world data indicates that multivariate methodology was better at predicting future events.