It has been repeatedly noted that stock price change distributions show high kurtosis
or "fat tails." This means that, if one looks at a time-series of observations on Sp or Ap,one sees long stretches of time when their(absolute) values are all rather small and
then an occasional extremely large (absolute)value. This phenomenon is commonly attributed to a tendency for new information to come in big lumps infrequently. There seems to be a common presumption that this information lumping might cause stock price
changes to have high or infinite variance,which would seem to contradict the conclusion
in the preceding section that the variance of price is limited and is maximized if forecasts have a simple autoregressive structure.