[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re[2]: [RT] HOW UNFORTUNATE



PureBytes Links

Trading Reference Links

On Saturday, June 02, 2001, 10:19:43 PM, Ira Tunik wrote:

IT> You are there requiring proof and back testing.

Asking for proof, yes, back testing, no. Stat analysis is quite
different from back testing.

IT> It has worked now for the past several decades.

It sounds like you have some very good back testing. :-)

IT> I assume that it will continue to work now.

It would also seem that you have enough 'seat-of-the-pants' stats to
warrant that assumption.

Some of us like to assess the stats for a long time period without
having to live through that period. For some new idea, one might do
this for the last 20 years in, say, an hour or two.

IT> You can test until your head caves in and get all those wonderful
IT> statistical results and the system won't make you any money.

It's not clear to me how a statistically good, well-tested system
would not make money. Other than trader error, how could this be?

IT> You can get better results then most traders by just throwing a
IT> dart at the stock listings and go long and liquidate at the end of
IT> the day.

Are you suggesting this would be better than a well-tested system?

IT> There is only one proof and that is your bottom line.  If that
IT> isn't increasing, no matter how good your statistical results are,
IT> you have a bad system or you are a bad trader.

Agreed. I was just suggesting that a system that has good stats might
be better than a system with bad stats.

ztrader



To unsubscribe from this group, send an email to:
realtraders-unsubscribe@xxxxxxxxxxxxxxx

 

Your use of Yahoo! Groups is subject to http://docs.yahoo.com/info/terms/