Selective Perception

Good out-of-sample results of a unique hypothesis may impress me but not naive statistics that demonstrate selective perception bias. Here is a recent example.

There has been a lot of unnecessary and unjustifiable noise in the financial blogosphere about the fact that the S&P 500 has not have a 1% range for quite some time, currently for 40 days, as shown in the chart below.

So many are impressed by the above fact because they are victims of selective perception. If we consider a daily range of 1.5% instead, this is what happens.

Now there is no new record but 64 days without a 1.5% range with a maximum of 116 days in 1993 and two occurrences of 100 days in 2005 and 2006. Now this (64 days ) is not impressive and this is the reason the 1% range is preferred because it shows a new record reading.

I am not impressed at all by selective perception. If you want to impress me with analysis, show me out-of-sample results of a unique hypothesis or portfolio in case of a data-mined hypothesis. Everything else is boring and a waste of time.

If you have any questions or comments, happy to connect on Twitter: @mikeharrisNY

Subscribe via RSS or Email, or follow us on Twitter.

Charting and backtesting program: Amibroker


Technical and quantitative analysis of Dow-30 stocks and 30 popular ETFs is included in our Weekly Premium Report. Market signals for longer-term traders are offered by our premium Market Signals service. Mean-reversion signals for short-term SPY traders are provided in our Mean Reversion report.

Copyright Notice

This entry was posted in Market Statistics and tagged , . Bookmark the permalink.

Leave a Reply