Wednesday, October 12, 2011

2011.10.12 DJIA Z-score of cycle model differences




Click on the image to enlarge.  To keep the chart simple on the cycle models, I use the absolute value of the z-score, since it is a symmetrical function. In this case, the sign value (+ or -) shows the direction of the expected reversal. Thanks to Greenface over at daneric's site for asking the question that inspired this.

Viewed in a historical context, this EOD chart suggests we are approaching historical extremes not seen since the mid-50's as well as other economically unpleasant periods in the past.

Edit on 2011.110.12 at 16:30:  I prettied up the chart and used EOD DJIA data rather than the 2:00 PM market price level.  The story is the same.

Visit econocasts.net for free sample trading model downloads. 

4 comments:

Paolo said...

Date Actual Pred. |Z|

2011.10.14 11644 9322 2.94
2011.10.17 11397 9186 2.85
2011.10.18 11577 9134 3.13
2011.10.19 11505 9136 3.03

Paolo said...

Date Actual Pred. |Z|

2011.10.14 11644 9322 2.94
2011.10.17 11397 9186 2.85
2011.10.18 11577 9134 3.13
2011.10.19 11505 9136 3.03
2011.10.20 11542 9196 3.00

Oliver said...

Thanks Paolo,

How long is 'too long' for the Z score to remain above 3 for confidence in the model to remain? Has there ever been instances in the past where it has remained elevated for an extended period of time?

Hope you don't mind all the questions...

Oliver

Paolo said...

How long is too long? I wish there were easy guidelines here. I think a week or two and I'd probably wonder about validity.

The last time z>=3 when the actual price was higher than the predicted price was between 08/23/1929 and 09/06/1929.