SI
SI
discoversearch

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor.  We ask that you disable ad blocking while on Silicon Investor in the best interests of our community.  If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.
Strategies & Market Trends : Take the Money and Run -- Ignore unavailable to you. Want to Upgrade?


To: John Pitera who wrote (17619)4/15/2013 3:03:32 AM
From: John Pitera  Respond to of 17639
 
these are posts from Jorjs thread ...........Take the Money and run..........

Hi Patick.... yes we are testing everything....... correlations can go from insanely consisted to absolutely breaking down...... the after spending 90 minuetes on saturday night we looked at a 3 dimensionaly corellation of the spread between the 2 and 10 year part of the yield curve and then overlaying the correlation of the SPX as well as third key monetary interest rate that I think I said I would not talk about in public........ I have some charts that we sit back and look at and it's got like 6 moving variables.....and sometimes they correlated massively and at other times such as 2008........ they completely break down..... the fact that they completely break down may well mean that these signals are the "canaries in the coalmine" and that they are leading indicators that we are preparing for a major financial meltdown........ and you know what that means in terms of shorting equities, running to treasuries...... and getting out of risk assets and currencies....... I'll see if I can post one on of these charts tomorrow........ I think I actually have to get clearance...... so as someone does not arrive at my door and sue me to death or more practically place 2 9 mm's in my head.

that would be very effective in shutting down my posting.

John



To: John Pitera who wrote (17619)4/15/2013 6:39:58 PM
From: Patrick Slevin  Respond to of 17639
 
I've done it now and then,

Create the Program, run it on sample data then walk forward with out of sample data.

It's a grind but some love doing it. Or appear to.