I predict there will be a lot of predictions of markets for the coming year. Here is a calibration of such predictions.
We show the prediction distribution of levels of several equity indices (plus oil price) at the end of 2011 assuming nothing happens. That is, we’ve taken out market trends and just left drift (more details below, and in tomorrow’s blog post).
[Revision: there was a problem with the computation of the plots below. You should ignore them in favor of the plots in Revised market prediction distributions.]
The distributions are very wide. If these distributions are even loosely correct, then we have very little basis to distinguish real market moves from random drift.
There will be more details in tomorrow’s blog post, but here is the outline of what was done:
- start with 8 years of returns
- take out an (excessively volatile) expected return at each point in time
- fit a GARCH(1,1) model
- simulate 250 trading days ahead starting with the current state
Figures may be reproduced with attribution.
Stock index data are from Yahoo. Oil price data are from the U. S. Energy Information Administration.
Flowingdata points to this musical recap of 2010: The Dow Piano.