Both of these models have reached extreme values of disparity between the actual price and the predicted price. Based on information from a completely different model for SLV I use to guide investment stance, my bet would be that silver will be the one that breaks down first but GLD is still in "buy mode" as of this moment.The concordance of the two models from the two time series supports validity, or the same structural flaw is present in the two models. This is unlikely but....
So, the possibilities remain:
- the model is valid (look out below! soon!)
- we are experiencing a "six-sigma" event but the model is valid (look out below, at some point)
- the model is not valid
Metals up on hope of Euro printing presses firing up. However here(US) we have negative guidance going forward and inventories are up and a forecast of recession. There's no error in the model. This is simply failing to accept the inevitable. Delayed reactions are numerous at the end. Going parabolic, hopium, denial, artificial props, excessive exuberance they all end in reality.
ReplyDeleteI wonder about the global village effect on the model. China, India and emerging markets are much more powerful than in the past. Caterpillar is looking at big profits going forward. Does the model properly compensate for the new global economy?
ReplyDeleteAnon, you state pretty much what I am thinking (option 1), but I have to keep open the possibility of major error.
ReplyDeleteThe answer to elViejo is Si!
I don't know about "properly" yet, I reckon we're about to find out.
Your site is interesting. I write software to control industrial processes and sometimes it requires a little modelling. Some processes require Self-Organizing-Fuzzy-Logic-Controllers. (SOFLIC) or Self Tuning PID Loop Controllers. It's funny how the code becomes self-referential. Douglas Hofstadter has just published a new book that looks interesting on self-referential nature.
ReplyDeleteYeah, in a sense, consciousness seems to be a Bayesian brain process matching perceived inner reality with perceived outer reality while acting on and creating both perceived realities. Loop de loop. Glitches in the process may explain how I get caught in the trap of occasionally but vigorously believing the BS I have generated.
ReplyDeleteYour work sounds interesting and challenging, and its nice to see someone here with SEM experience.
Yep, Bayes is enjoying a resurgence. I read this Science News Article last week:
ReplyDeletehttp://www.sciencenews.org/view/feature/id/334571/title/The_Probabilistic_Mind
BTW I was Anonymous earlier - accidently clicked anon.