|
PureBytes Links
Trading Reference Links
|
UM,
To me the results are “flawed” if they don’t take these things into account.
When’s the next or 10/19/87 or 9/11/01 etc. ? I certainly don’t pretend to know but I certainly want to know which way my systems were invested or not during these times.
Fred
> Hi Fred.
>
> > With regards to your post at amibroker-ts (Ignoring extreme price
> > changes) IMHO the more one "ignores" the effect of real world events
> > on prices the more one is subject to them in the real trading.
>
> my point of view is that at least during the development and testing
> phase a system should simply filter out extreme price changes, because
> such extremes bring the indicators out-of-order... As I wrote, by this
> I do mean "normal" systems only, and not those systems which are
> aimed exactly on such extreme situations. It is a conservative and
> risk minimizing strategy if one filters such rare(?) events out. Otherwise
> the backtesting results could be "flawed" because of only one or two
> of such events with possibly big impact on the result; ie. the overall
> result would not be statistically significant or correct.
>
> UM
Yahoo! Groups Sponsor
Send BUG REPORTS to bugs@xxxxxxxxxxxxx
Send SUGGESTIONS to suggest@xxxxxxxxxxxxx
-----------------------------------------
Post AmiQuote-related messages ONLY to: amiquote@xxxxxxxxxxxxxxx
(Web page: http://groups.yahoo.com/group/amiquote/messages/)
--------------------------------------------
Check group FAQ at: http://groups.yahoo.com/group/amibroker/files/groupfaq.html
Your use of Yahoo! Groups is subject to the Yahoo! Terms of Service.
|