On Mar 12, 2007, at 11:29 AM, Miles Jackson wrote:
> This is pretty rich: Hubbert used his model in the 1950s to correctly
> predict the peak of U. S. oil production in the 1970s! Economists'
> misconceptions notwithstanding, it turns out you can effectively
> predict
> the future with a well-specified regression model.
As I recall the finance literature, there's not enough of a history to state authoritatively that stock returns are significantly different from zero over the long term. Since we've had stock markets for several centuries, that's a lot of data that still falls short of significance. So how can we generalize from Hubbert's n=1?
Doug