Thursday, October 6, 2011

Cycle Models Silver Long $ Short Term Predictions
















No, this Silver model is not a mistake.  It is the latest structural equation model.  I have been doing silver model updates mid-week because I was expecting the possibility of a model bifurcation given the differences in long-term predictions between two usually correlated metals comparing the older silver model with the present gold model. I was rewarded early this morning having watched the "parameter screen" with utter amazement, feeling like I was watching a screen in the Matrix. The new model slowly collapsed two longer fractal cycles into one cycle.  This is always a Good Thing because the fewer parameters, the better the model.

If you look closely, on the short term side, there is no significant difference between the old and new silver model in the short-term.  Both predict a downdraft.   The new model shows a much different longer term prediction, which is more in line with the gold model, and in line with a deflationary depression. It was hard trying to see how gold could go one way and silver another for a prolonged period of time.  It turns out that in statistics speak, there is not much difference between the old and new silver model - we are simply looking at two possible outcomes of almost even probability.

Taken together, my observations on the two models point to the new silver model as having better predictive accuracy, but not because of model statistics - this is my opinion. I will continue to run both old and new silver models to see if the next few days the new model declares itself as statistically better.  Or not.  Meanwhile, I am posting the new silver cycle model as the default model.

5 comments:

Rajeev Bharol said...

Thanks a lot. Now it makes more sense to see both Gold and Silver going in the same direction.

Rajeev Bharol said...

Hi,
Can you please run the model on Dow for the data only up to year 2000 and see if it would have predicted the direction from 2000 to now?

Paolo said...

Hi Rajeev, regarding your comment on the DJIA, this might help.
Econocasts business cycle chronicles: Historical Cycle Model DJIA using data up to 12/31/99

Rajeev Bharol said...

Thanks a lot. That is helpful.

Paolo said...

I'm glad it helped.