Oct

23

TA Patterns, from James Sogi

October 23, 2009 |

J SogiNow that statistical quant is being denigrated on the Street, I am seeing these old TA John Magee patterns that haven't worked for years appearing. Like broadening top. Anyone else?

One of the weaknesses of statistics is the problem of changing cycles, and the appearance of hidden or unknown variables in a data series. Though it is prospective looking, it still uses historical data. The other issue is the role of randomness where very very long runs can appear, even in random series.

Bruno Ombreux defends statistics:

I don't think statistics are weak, but the present environment is unique. For decades, we enjoyed a relatively stable environment and a capitalistic system. This has changed. All bets are off.

The problem is that the type of environment we are in, for instance consumer deleveraging while the Fed is money printing, has not happened very often. There are some similar situations in the 1950s, and some in the 1930s. That's not a lot. Therefore we can't even condition on the environment, because we don't have enough data for such environment.

I had come to rely on statistics. For the past few months, nothing has been working for me. I am not having a good year. Actually, this is my worst year since 1999 (compared to the index) and since 2002 (in absolute terms).


Comments

Name

Email

Website

Speak your mind

Archives

Resources & Links

Search