Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > comp.os.linux.advocacy > #117188

Re: Grubbs_Nov2007-May2012

Show all headers | View raw

On 7/2/12 8:46 AM, in article
ee6feae0-a668-46ac-97a8-cf3a09b0f4c1@googlegroups.com, "cc"
<scatnubbs@hotmail.com> wrote:

... 
>>> Can you provide a link to the website where the full set is? I would like to
>>> verify your results from the source. Thanks.
>> 
>> I already anticipated that you would need verification, given how you
>> pointed to the site (the one we had already been agreed on) but never showed
>> you had any clue how to get the longer term stats:
>> <http://tmp.gallopinginsanity.com/NetMarketShareStats.mov>
> 
> I see you followed the exact directions I gave to you. So you're lying when
> you say I didn't have the full set. Remember, I had to tell you three times
> how to get to them. I guess maybe I should have made a movie for you, since
> you can't read.

You made the above up - you gave no "exact directions".  You lied.  Any not
only did you not show you had the full set, you made claims about the full
set that have been shown to be false.  As is your norm when you are proved
to be lying, you snipped what you could not handle:

>> What calculators did you try?  Please show me one that shows:
>> 
>>   cc:
>>     -----
>>     There are four outliers in the latter half of 2011.
>>     -----
>>     There are some low numbers sprinkled in there from late 2007,
>>     early 2008, that are also outliers, if you can't figure that
>>     out for yourself.
>>     -----
>>     But that doesn't change the fact that those data points are
>>     statistically insignificant because they are outliers.
>>     -----
>>     There is a well-defined (several actually) method for
>>     determining outliers. This is a fact. I found the outliers,
>>     you did not.
>>     -----
>>     Your new trendline uses data made up of mostly outliers,
>>     evidenced by all standard measurements of outliers and the
>>     fact that a single state caused the fluctuation.
>>     -----

Whoops... you never answered that question.  I have certainly made a good
faith effort, and more, to replicate what you claimed to find:

<http://tmp.gallopinginsanity.com/Grubbs-Quartile_Nov2007-May2012.pdf>
<http://tmp.gallopinginsanity.com/median_and_array.pdf>
<http://tmp.gallopinginsanity.com/BoxPlot.pdf>

In the end, your claims could not be replicated with any of the following
mathematical models:

    1) Median() and Array
    2) Grubbs
    3) Quartile
    4) Box Plot

Given how you specifically mentioned at least one of those methods this is
odd.  Maybe you used different parameters.  Well, I have shown all my work
and even made my Excel spreadsheets available.  You have not.  And you never
will - you just made things up in your above claims.  It has always been
clear - but with the work I have done I think we can clearly say it has been
proved.  You lied.  Your claims were based on your wishes - you never did
the work you claimed and just hoped I would not do the work to prove you
wrong.

But I did.

You lied.  Again.  There is no doubt about this.  See my .sig for more
examples of where you were busted lying and/or just being outright wrong.


-- 
Summary of cc's statistical BS: <http://tinyurl.com/7rwazxw>
Details on cc's "outliers" BS: <http://tinyurl.com/84r3ypq>
More on cc's ignorance about outliers: <http://tinyurl.com/7vyhttc>
Four method compared to cc's absurd claims: <http://tinyurl.com/7efkuzm>
Details on cc's sigma and R^2 BS: <http://tinyurl.com/7vambev>

Back to comp.os.linux.advocacy | Previous | Next — Previous in thread | Find similar

Thread

Re: Grubbs_Nov2007-May2012 Snit <usenet@gallopinginsanity.com> - 2012-06-29 09:19 -0700
  Re: Grubbs_Nov2007-May2012 cc <scatnubbs@hotmail.com> - 2012-07-02 04:44 -0700
    Re: Grubbs_Nov2007-May2012 Snit <usenet@gallopinginsanity.com> - 2012-07-02 08:41 -0700
      Re: Grubbs_Nov2007-May2012 cc <scatnubbs@hotmail.com> - 2012-07-02 08:46 -0700
        Re: Grubbs_Nov2007-May2012 Snit <usenet@gallopinginsanity.com> - 2012-07-02 09:01 -0700

csiph-web