Silicon Investor (SI) -- The First Internet Community

STOCKTALK

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.

Pastimes : Nasdaq Bottom? -- Ignore unavailable to you. Want to Upgrade?

To: GROUND ZERO™ who wrote (41)	12/31/2000 7:45:03 AM
From: Moominoid	Read Replies (1) \| Respond to of 73

I would define a top if looking at the data following the top you could find a statistically significant negative trend in that data and a statistically significant positive trend in the data in the period before the top. Now exactly as you (GZ) say there are tops at all kinds of scales. The longer the time distance between observations the longer the period of observation required to confirm a top. I think the "permabears" are talking about tops in the index on at least monthly scales and maybe quarterly or longer resolution. But they need to be clear about the scale. I guess I'll have to do some tests on the indices and check there hasn't been a top yet. IMO the correct test is to take the logarithmic change in the index from period to period (log first difference) and then calculate the t-statistic Mean/Standard Deviation. This has the t-distribution. So bigger than 2 means an uptrend with 95% probability less than -2 a downtrend etc. This procedure is appropriate to the nature of the data (a random walk). Well actually second differencing might be necessary ... :) David