Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > comp.os.linux.advocacy > #116583
| From | Snit <usenet@gallopinginsanity.com> |
|---|---|
| Newsgroups | comp.os.linux.advocacy |
| Subject | Re: A lesson on outliers for cc |
| Date | 2012-06-28 11:17 -0700 |
| Message-ID | <CC11EDCC.422F%usenet@gallopinginsanity.com> (permalink) |
| References | <CC113D82.41B3%usenet@gallopinginsanity.com> <e8ea4840-103b-476c-975b-623b019d75a4@googlegroups.com> <CC11D687.4217%usenet@gallopinginsanity.com> <6660dd25-efb5-4f53-a20a-ce484918176c@googlegroups.com> |
On 6/28/12 10:17 AM, in article
6660dd25-efb5-4f53-a20a-ce484918176c@googlegroups.com, "cc"
<scatnubbs@hotmail.com> wrote:
> On Thursday, June 28, 2012 12:38:15 PM UTC-4, Snit wrote:
>> On 6/28/12 5:51 AM, in article
>> e8ea4840-103b-476c-975b-623b019d75a4@googlegroups.com, "cc"
>> <scatnubbs@hotmail.com> wrote:
>>
>>> On Thursday, June 28, 2012 1:45:22 AM UTC-4, Snit wrote:
>>>>> -----
>>>> Diagnosing Outliers
>>>>
>>>
>>>
>>> I used quartiles and avg+stddev. Two different methods and both achieved the
>>> same results.
>>
>> Ah, more snipping from you. But let us look at your "methods". The
>> quartile method:
>
> What method did you use again? Oh right, you didn't even think to look for
> outliers.
>
>> <http://tmp.gallopinginsanity.com/outlier-quartiles.pdf>
>>
>> What? Only two points! But you claimed four! Where did you get the other
>> two? Just make them up? Screw up your own selected method? Or are you
>> going to claim that this method is wrong? But wait! There is more!
>
> Using Moore and McCabe you get two outliers. Excellent. But you're also not
> using the full set of data available. But at least you're starting to see that
> some of the important points you're using are indeed outliers.
Ah, yes, your continual change of what data set you want to use. Got it.
>> <http://en.wikipedia.org/wiki/Quartile>
>> -----
>> There is no universal agreement on choosing the quartile values.
>> -----
>>
>> Here are just some of the methods:
>>
>> <http://mathworld.wolfram.com/Quartile.html>
>> -----
>> Minitab
>> Tukey (Hoaglin et al. 1983)
>> Moore and McCabe (2002)
>> Mendenhall and Sincich (1995)
>> Freund and Perles (1987)
>> -----
>>
>> So which did you use? Maybe you used one that would point to four points...
>
>> but based on the information you snipped, this *still* would be a silly way
>> to do things *hence the reason you snipped it*!
>
> One of my methods was Grubbs
And yet you claim to come up with four points.
<http://tmp.gallopinginsanity.com/outliers-grubbs.pdf>
And that is with a standard significance level of 0.05. And it finds *one*
point.
But, wait, there is more.
<http://graphpad.com/faq/viewfaq.cfm?faq=1598>
The Grubbs method assumes a Gaussian population... a normal distribution.
Oops!
So you used an inappropriate method and either calculated it incorrectly
*or* set your significance level at an absurd level.
As noted: you screwed up. This keeps being pointed out to you and you just
snip and run, as you will here. As such, it is clear you know you are
ignorant on this topic... you are just making things up as you go.
>, the other IQ, and it is certainly NOT a silly
> way to do things. I snipped some paragraphs where you tried to understand what
> was being said and totally failed.
You snipped info you know proves you wrong. Let us not pretend otherwise.
>> -----
>> Non-Parametric Extremity
>>
>> Another approach to measuring divergence is through
>> non-parametric methods. Essentially, the concept is the same,
>> and the mean is still the center; however the divergence is
>> measured by the inter-quartile range (IQR). Essentially, you
>> order your data set and then break it into four equal parts.
>> The lowest 25% is your first quartile; the next 25% is your
>> second quartile (whose upper bound is the median); and so on.
>> Essentially, anything higher than the top of the third
>> quartile or lower than the bottom of the second quartile is
>> reviewed for outliers.
>>
>> If done haphazardly, non-parametric extremity will give you
>> the same problem as establishing a set percentage on both
>> ends as outliers. To avoid this drawback, again inspect the
>> points that fall outside the second and third quartiles.
>> Those closest to the outer bounds of the IQR can remain in
>> your data set; those far away should be measured for
>> accuracy, and if accurate can be adjusted or removed.
>> -----
>>
>> But you do not even know what any of that means. :)
>
> I do.
You have already demonstrated otherwise. Let us not pretend you have not.
That would be dishonest.
> Any method has drawbacks. But it was not done haphazerdly. There was
> nothing haphazerd about it, so the drawbacks are minimal. None of the four
> points in question were close to the outer bounds.
Well, if you use whatever flawed method you used to find *four* points.
<http://tmp.gallopinginsanity.com/outliers-grubbs.pdf>
But let me guess: just like you think the MS site is wrong and the Apple
site and the other sites that speak of how to get a linear trend line, you
think the graphpad.com calculator is also wrong.
Only you know the "right" answers. LOL!
> What method did you use to test for outliers again? Oh right, you didn't even
> bother, because you're an idiot.
LOL! You really like to advertise you have no idea what is being discussed!
>>> Do you have a problem with the QUARTILE function in Excel?
>>> Do you have a problem with the AVERAGE function in Excel?
>>> Do you have a problem with the STDDEV function in Excel?
>>
>> Never suggested I did. I do not even have a problem with your pretending to
>> understand what you are doing as you lie and snip and run and show off your
>> ignorance - in fact, I *enjoy* it!
>
> Well if you have no problems with my calculations, or methods, then you should
> have no problem with me identifying those points as outliers. You've given one
> method so far that has two points as outliers. But you didn't even use all the
> data available to you. You're doing an incredibly poor analysis my friend.
I have discussed multiple methods and why it is easy to prove you wrong.
And it is.
And your snipping shows you know that.
>>> If so, then let us know and I will calculate by hand and put up the results
>>> again. If not, then there is no argument against those points being
>>> outliers. If you would like to use a different method, THEN SHOW YOUR WORK.
>>>
>>> The actual percentage of outliers is not 17%. There is data on the website
>>> back to 2007. Those points you're denying are outliers only make up 6%.
>>>
>> What data are you using? And show your specific method of determining these
>> as outliers. Also explain why you are now looking at a *different* data set
>> than the one you asked me to look at.
>>
>> But you will not. You will run. It is what you do.
>
> I'm using all the data to check for outliers.
All the data you asked me to use or some other set of data?
And in *all* that data, which you will not list, you found only four
outliers and they were *all* in the latter half of 2011.
That is absurd. You are again showing off your dishonesty.
> That is not the same as picking a subset to get a trend line over. Why would
> you throw away data when trying to find outliers? More data would obviously
> give you a better chance at finding outliers. The data I'm using is all the
> data available on the website where you picked your small subset from. It goes
> back to 2007.
So show this data. And then explain why you only found four outliers and
*all* of them happen to be from the latter half of 2011.
>>> Since it was only California that caused the spike in the numbers, OUT OF
>>> THE ENTIRE WORLD, then you would be hard pressed to find any statistician of
>>> any worth who wouldn't call those points outliers.
>>>
>> Only California. Interesting claim!
>>
> You can apply filters on the website and see for yourself. At the peak,
> California was at 18%. It's dropped off a staggering amount to 10% now. It had
> a much larger increase/decrease than the rest of the world, and definitely
> skewed the results.
>
> Hmm, so I tested for outliers, found which points they were, then found out
> why they are outliers. Interesting isn't it? You couldn't be bothered to even
> check for outliers in the first place. You're way out of your league, little
> buddy.
I found the post on California and responded... and finding the regional
data had nothing to do with your faulty methods you screwed up.
>>> You're so desperate to try and be right that you've narrowed your prediction
>>> down (which was once open-ended and "very obvious") to 6 months at the end
>>> of 2011 and ONLY IN CALIFORNIA. You go girl.
>>>
>> Please keep in mind you have been proved wrong - and you also have shown,
>> with your snipping, that you know you are wrong. But if you think you can
>> show otherwise then go for it!
>>
>
> You're hilarious if you think you are somehow right in all this. Take out
> California and you get a relatively flat Linux usage WORLDWIDE. Now, what do
> you think that means?
Your BS is fully refuted, below. Stop snipping and running.
--
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>
Details on cc's sigma and R^2 BS: <http://tinyurl.com/7vambev>
Back to comp.os.linux.advocacy | Previous | Next — Previous in thread | Next in thread | Find similar
A lesson on outliers for cc Snit <usenet@gallopinginsanity.com> - 2012-06-27 22:45 -0700
Re: A lesson on outliers for cc Onion Knight <onionknightgot@gmail.com> - 2012-06-27 23:10 -0700
Re: A lesson on outliers for cc Snit <usenet@gallopinginsanity.com> - 2012-06-27 23:45 -0700
Au revoir (killfile extension) Chris Ahlstrom <ahlstromc@xzoozy.com> - 2012-06-28 06:16 -0400
Re: Au revoir (killfile extension) Foster <frankfoster50@yahoo.com> - 2012-06-28 08:37 -0400
Re: Au revoir (killfile extension) Peter Köhlmann <peter-koehlmann@t-online.de> - 2012-06-28 14:47 +0200
Re: Au revoir (killfile extension) Peter Köhlmann <peter-koehlmann@t-online.de> - 2012-06-28 14:54 +0200
Re: Au revoir (killfile extension) Foster <frankfoster50@yahoo.com> - 2012-06-28 08:58 -0400
Re: Au revoir (killfile extension) Snit <usenet@gallopinginsanity.com> - 2012-06-28 09:09 -0700
Re: Au revoir (killfile extension) Foster <frankfoster50@yahoo.com> - 2012-06-28 08:58 -0400
Re: Au revoir (killfile extension) chrisv <chrisv@nospam.invalid> - 2012-06-28 08:04 -0500
Re: Au revoir (killfile extension) Foster <frankfoster50@yahoo.com> - 2012-06-28 09:07 -0400
Re: Au revoir (killfile extension) DFS <nospam@dfs.com> - 2012-06-28 09:34 -0400
Re: Au revoir (killfile extension) Snit <usenet@gallopinginsanity.com> - 2012-06-28 09:11 -0700
Re: Au revoir (killfile extension) Chris Ahlstrom <ahlstromc@xzoozy.com> - 2012-06-28 09:54 -0400
Re: Au revoir (killfile extension) cc <scatnubbs@hotmail.com> - 2012-06-28 07:24 -0700
Re: Au revoir (killfile extension) Snit <usenet@gallopinginsanity.com> - 2012-06-28 09:02 -0700
Re: Au revoir (killfile extension) Foster <frankfoster50@yahoo.com> - 2012-06-28 19:40 -0400
Re: Au revoir (killfile extension) Marti Van Lin <ml2mst@dontevenbother.invalid> - 2012-06-29 09:29 +0200
Re: Au revoir (killfile extension) William Poaster <wp@induh-vidual.net> - 2012-06-29 10:37 +0100
Re: Au revoir (killfile extension) Hadron<hadronquark@gmail.com> - 2012-06-29 11:42 +0200
Re: Au revoir (killfile extension) Peter Köhlmann <peter-koehlmann@t-online.de> - 2012-06-29 11:47 +0200
Re: Au revoir (killfile extension) Chris Ahlstrom <ahlstromc@xzoozy.com> - 2012-06-29 06:13 -0400
Re: Au revoir (killfile extension) William Poaster <wp@induh-vidual.net> - 2012-06-29 11:23 +0100
Re: Au revoir (killfile extension) Foster <frankfoster50@yahoo.com> - 2012-06-29 10:28 -0400
Re: Au revoir (killfile extension) Foster <frankfoster50@yahoo.com> - 2012-06-29 10:27 -0400
Re: Au revoir (killfile extension) GreyCloud <mist@cumulus.com> - 2012-06-29 13:10 -0600
Re: Au revoir (killfile extension) DFS <nospam@dfs.com> - 2012-06-29 08:31 -0400
Re: Au revoir (killfile extension) DFS <nospam@dfs.com> - 2012-06-29 08:29 -0400
Re: Au revoir (killfile extension) Foster <frankfoster50@yahoo.com> - 2012-06-29 10:26 -0400
Re: A lesson on outliers for cc Peter Köhlmann <peter-koehlmann@t-online.de> - 2012-06-29 11:49 +0200
Re: A lesson on outliers for cc Onion Knight <onionknightgot@gmail.com> - 2012-06-27 23:27 -0700
Re: A lesson on outliers for cc cc <scatnubbs@hotmail.com> - 2012-06-28 05:51 -0700
Re: A lesson on outliers for cc Snit <usenet@gallopinginsanity.com> - 2012-06-28 09:38 -0700
Re: A lesson on outliers for cc cc <scatnubbs@hotmail.com> - 2012-06-28 10:17 -0700
Re: A lesson on outliers for cc Snit <usenet@gallopinginsanity.com> - 2012-06-28 11:17 -0700
Re: A lesson on outliers for cc cc <scatnubbs@hotmail.com> - 2012-06-28 11:32 -0700
Re: A lesson on outliers for cc Snit <usenet@gallopinginsanity.com> - 2012-06-28 13:50 -0700
Re: A lesson on outliers for cc cc <scatnubbs@hotmail.com> - 2012-06-28 14:01 -0700
Re: A lesson on outliers for cc Snit <usenet@gallopinginsanity.com> - 2012-06-28 14:30 -0700
Re: A lesson on outliers for cc cc <scatnubbs@hotmail.com> - 2012-06-28 14:34 -0700
Re: A lesson on outliers for cc Snit <usenet@gallopinginsanity.com> - 2012-06-28 14:48 -0700
Re: A lesson on outliers for cc cc <scatnubbs@hotmail.com> - 2012-06-28 14:52 -0700
Re: A lesson on outliers for cc Snit <usenet@gallopinginsanity.com> - 2012-06-28 15:17 -0700
Re: Grubbs_Nov2007-May2012 Snit <usenet@gallopinginsanity.com> - 2012-06-28 15:59 -0700
Re: Grubbs_Nov2007-May2012 Onion Knight <onionknightgot@hotmail.com> - 2012-06-29 04:36 -0700
Re: Grubbs_Nov2007-May2012 Snit <usenet@gallopinginsanity.com> - 2012-06-29 09:19 -0700
Re: Grubbs_Nov2007-May2012 Onion Knight <onionknightgot@gmail.com> - 2012-06-29 22:15 -0700
Re: Grubbs_Nov2007-May2012 Snit <usenet@gallopinginsanity.com> - 2012-06-30 11:05 -0700
Re: Median_and_Array_Nov2007-May2012 Snit <usenet@gallopinginsanity.com> - 2012-06-28 20:56 -0700
Re: A lesson on outliers for cc cc <scatnubbs@hotmail.com> - 2012-06-28 14:14 -0700
Re: A lesson on outliers for cc Snit <usenet@gallopinginsanity.com> - 2012-06-28 14:36 -0700
Re: A lesson on outliers for cc cc <scatnubbs@hotmail.com> - 2012-06-28 14:42 -0700
Re: A lesson on outliers for cc Snit <usenet@gallopinginsanity.com> - 2012-06-28 14:51 -0700
Re: A lesson on outliers for cc Snit <usenet@gallopinginsanity.com> - 2012-06-28 20:52 -0700
Re: A lesson on outliers for cc Onion Knight <onionknightgot@hotmail.com> - 2012-06-29 04:33 -0700
Re: A lesson on outliers for cc Snit <usenet@gallopinginsanity.com> - 2012-06-29 09:03 -0700
Re: A lesson on outliers for cc Snit <usenet@gallopinginsanity.com> - 2012-06-28 09:45 -0700
csiph-web