--- In [email protected], "authfriend" <[EMAIL PROTECTED]> > > 
> > Why is that so important to you.
> 
> It's important to understanding the study.  It's being
> used as a way to suggest they changed things around
> after seeing the data to get a better result, which isn't
> what happened.  

Additional variables not anticipated at the beginning of data
collection are tested post study all the time. Its not a sign of
fudging. There are other signs that indicate fudging, IMO, but not
testing a more comprehensive set of control variables. Your concern is
misplaced.

> And you're using it to construct all kinds
> of speculations about their methodology.  It's just
> ridiculous.

haha. ok . If you say so. Again, i am simply trying to understand what
the study did. I am waiting for a coherent explanation. if in the
absence of that, I speculate a bit, what is the problem?
 
>  
> > Regardless, can you tell me what analysis was added in the second
> > round of analysis (the 25% result), relative to the the first round
> > (the 17%) -- per LBS' post?
> 
> Not a clue, sorry.

And yet thats a major part of the analysis. Which I am trying to
understand. Speculation can actually be a tool here.
 
>  it may seem so based on
> > your level of knowledge of modeling, I don't know. Its a
reasonable speculation on what the study actually did, based on the
sparseness  of coherent explanations.
> 
> No, it's not reasonable to speculate at all about
> this sophisticated a level of statistical analysis.

OK, if you say so. I disagree.
 
> > I am trying to understand what they did. Your explanations are not
> > grounded in knowledge of regression and ARIMA, so it appears to be
a pretty unproductive exercise.
> 
> Yes, that's what I'm saying.  I can't guide you on
> the fine points of the statistical methodology, I
> can only tell you the broad outlines.  So for you to
> then try to make fine-grained analysis on the basis
> of guessing is, as I said, just silly.

if i made fine grained analysis I supposed so. I am simply trying to
underststand the broad outlines of the analysis. What methods were
used, what were the model specifications tested (and rejected) and
"kept". This is basic, basic stuff.
> 
>  So perhaps we should
> > get a copy of the study. Do you have access?
> 
> Oh, please.  What is your *problem*?  If I did, obviously
> I'd have posted it here long since.  That's a disingenuous
> question.

jeez.  it is a simple question.  you might have a hard copy. You might
know somone who has it. lighten up.
 
> You could get an offprint of the article from the
> journal, most likely.
> 
> > Also you said the data set is public. Where? How is it accesssed?
> 
> FBI crime stats.  They may be on the Web, or you might
> have to go to a library or something.
>

okie dokie






------------------------ Yahoo! Groups Sponsor --------------------~--> 
Get fast access to your favorite Yahoo! Groups. Make Yahoo! your home page
http://us.click.yahoo.com/dpRU5A/wUILAA/yQLSAA/JjtolB/TM
--------------------------------------------------------------------~-> 

To subscribe, send a message to:
[EMAIL PROTECTED]

Or go to: 
http://groups.yahoo.com/group/FairfieldLife/
and click 'Join This Group!' 
Yahoo! Groups Links

<*> To visit your group on the web, go to:
    http://groups.yahoo.com/group/FairfieldLife/

<*> To unsubscribe from this group, send an email to:
    [EMAIL PROTECTED]

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


Reply via email to