Hello Drew,

Thanks.
Looking forward to your follow up.

For me, things got curiouser and curiouser when Mr Aronson's treatise 
on *Detecting Data Mining Bias* called for *out of sample* testing.
However, I will reserve comment until after I read the book ( a few 
weeks delivery to my locale).

I think we should do everything in our power to disprove the OOS/walk-
forward hypothesis.
There are only two possible outcomes; prove it wrong enough by 
finding something better or prove it correct enough by failure to do 
so.

For the benefit of the nervous, I am not going to leave one wobbly 
hypothesis for an even wobblier one.

We could also positively reshape the objective to comfort the OOS 
faithful:

*That our IS analysis is so good that every time we submit an IS 
accepted system to OOS testing it passes*.

BrianB2 *:-)

--- In [email protected], "thomasdrewyallop" <[EMAIL PROTECTED]> 
wrote:
>
> Hello all,
> 
> I have been working on the MCP technique described in Aronson's book
> for some time now. I have just completed conversion of the C++ code 
on
> the web site to C# plus some associated utlities to massage AB data
> into the required format yet. No test yet; I will update under this
> thread.
> 
> A few words on the theoretical underpinnings. There has been new
> information since the book was published and the code written. I
> believe an update is in the works. Also you need to be cautious when
> running MCP on IS data. This is only valid under certain conditions.
> Otherwise you must run OOS. I had an email from Aronson explaining 
all
> this but can't find it. You might want to contact David directly - a
> good guy and willing to talk with readers.
> 
> Finally, I would not reject walk forward. A very useful technique
> despite Aronson's reservations. Well integrated with AB too via Fred
> Tonetti's IO add-in.
> 
> Best regards,
> 
> Drew Yallop
> 
> p.s. just remebered that there is discussion on MCP as a possible
> future addition to AB. Look in the AB suggestions section of the 
web site.
>


Reply via email to