Cold Reading Demos at TAM2

That is a perfect example, Thanz (at least for those of us who hope that Bill's selection of his method was due to a bias he was unaware of. Hopefully, his choice of a method that would support the conclusion he wanted was inadvertent--as was his intractable defense of it when others used methods that yielded quite different results. :p ).
Posted by T'ai Chi

You fail to intimidate me with the tactic of attributing something to me then arguing against me with what you invented.
Yes, that sounds familiar.
I only referred to conscious or unconscious bias (hence the need for blinding). You are pathetically attempting to make it appear as I claimed this is a "supernatural ability". It simply won't work Claus.
What is Claus saying, T'ai Chi? That there is no such thing as rater bias (either consciously or not?)? That would be a very odd position. Isn't bias, as you say, one of the reasons the blinding of the evaluator/statistician is so important? (Think Schwartz, Claus.)

Saying a rater may subconsciously, with no -intent- of skewing the data pro or con, select a method of statistical analysis that will be most likely to yield the result the investigator wants ("rater bias") is a "supernatural claim"? Really? Since when? :confused:
 
T'ai Chi said:
:rolleyes: That's not a stat. knowledge error, that is a looking at the wrong row for output error. Oops.
This is paradoxical.
A poster who states that stat rats must be blinded so they don't make stupid (nod, nod, wink, wink. Say she goes, say she goes?) or biased misteaks in their data anal ysis, makes an egregious mistake in looking up the wrong row of a table to bolster his naive opinion.
 
Thanz said:
Heck, I can answer that!

That's nice. But, quite frankly: I did not ask you. I asked T'ai Chi. I would appreciate it, if you could let T'ai Chi fend for himself.

I'm sure that T'ai Chi would appreciate this, too. Although I don't hold T'ai Chi in the highest regard, I am fairly confident that he would appreciate the opportunity not to appear as a stooge, but as an independent human being, capable of defending his own views.

Your example can be discussed in the thread where it originated, by the people who were participating.

I'm sure you cannot object to this.
 
CFLarsen said:

(snip)
You claimed, that a statistician could - unconsciously - choose the method that shows his own biases. That is not "supernatural"? Then, what is?


Unconscious bias is not supernatural as I've already stated and you continue to ignore. As I've already pointed out, an evaulator could unconsciously select a method that yields larger or smaller p-values, or estimates in general. Needless to say, without blinding, an evaluator could also make his comments on the analysis incredibly biased, consciosuly or unconsciously, if he knows the group memberships.
 
Jeff Corey said:

Sorry, Mr. B.S and M.S. in stat, you failed the test.


Wrong.


"Stat. knowledge" should include the ability to discern the right row and report the results correctly.


Oh please, that is an honest error.


Better check the value of .0218 for the non-Yates computation of chi-square ( two tailed). I got .0219.


So? Rounding perhaps is the issue. You're now going to argue about a 4th decimal place? Whatever.


Was your average grade in your stat classes near the median of the class? Or were you the standard deviation? It means no differential to me.

You evaded the results of the updated Fisher's vs Chi square tests. Feel free to actually address them instead of focusing on me.
 
Clancie said:
What is Claus saying?

You know exactly what I am saying. I don't know why you want to make a fool out of yourself by claiming that you have me on ignore, because everyone knows that you do not.

People know this, because you yourself have admitted that you don't. But, OK, be a fool.

Clancie said:
That there is no such thing as rater bias (either consciously or not?)? That would be a very odd position. Isn't bias, as you say, one of the reasons the blinding of the evaluator/statistician is so important? (Think: Schwartz)

No, that is not what I am saying, and you know it.

Clancie said:
"Rater bias" is a supernatural claim? Says who? :confused:

Please read what T'ai Chi is claiming: That a statistician can unconsciously choose the method that shows his own bias.
 
BillHoyt said:

Don't retract it, then, but show us the evidence. Cite the papers wherein the principal researchers acknowledge you or thank you for your assistance. It is done all the time. In fact, it is tremendously disrespectful not to do this. If you consulted on a paper, you were acknowledged. Where can we find those papers? Ladies Home Journal?

Not the issue at all.

For what it is worth, they were for students' Ph.D and M.S. theses (which they did very well on). Your attempt at changing the topic is noted.
 
CFLarsen said:


That's nice. But, quite frankly: I did not ask you. I asked T'ai Chi. I would appreciate it, if you could let T'ai Chi fend for himself.

I'm sure that T'ai Chi would appreciate this, too. Although I don't hold T'ai Chi in the highest regard, I am fairly confident that he would appreciate the opportunity not to appear as a stooge, but as an independent human being, capable of defending his own views.

Your example can be discussed in the thread where it originated, by the people who were participating.

I'm sure you cannot object to this.
As far as I could tell, your interactions with T'ai Chi had devolved to the level of "Taste Great!" "Less Filling!!" and I thought some fresh perspective might be appreciated.

From your response, it would appear that you are less interested in getting an actual answer to your question than you are in badgering a particular poster.

If you are actually interested in the ideas behind your question, I invite you to discuss my example in this thread. I see no need to resurrect an old thread to discuss my example. I think that it is an appropriate example of a statistician choosing a method that shows his biases.

If you are not interested in the answers, why ask the questions?
 
Jeff Corey said:

A poster who states that stat rats must be blinded so they don't make stupid (nod, nod, wink, wink. Say she goes, say she goes?) or biased misteaks in their data anal ysis, makes an egregious mistake in looking up the wrong row of a table to bolster his naive opinion.

You are equating a statistician working on an experiment with me doing some quick calculations for an internet bulletin board? O.K.

Please address the results of the updated Fisher's Exact test vs. Chi square test.

Thanks.
 
CFLarsen said:

Please read what T'ai Chi is claiming: That a statistician can unconsciously choose the method that shows his own bias.

I said that evaluators can show conscious and unconscious bias.

Note that Claus claimed that I said this is a "supernatural ability". :rolleyes:
 
T'ai Chi said:
I said that evaluators can show conscious and unconscious bias.

Note that Claus claimed that I said this is a "supernatural ability". :rolleyes:

Yes, I did. Could you please explain why it is "natural" for a statistician to be able to unconsciously choose the method that shows his own bias?

It is very simple, T'ai Chi. And, after you do this, could you please explain how it is done?

You keep dodging these questions, but they won't go away.

If you feel these questions amount to abuse, I implore you to contact the mods.

Otherwise, I would very much like answers.
 
T'ai Chi said:
Unconscious bias is not supernatural as I've already stated and you continue to ignore. As I've already pointed out, an evaulator could unconsciously select a method that yields larger or smaller p-values, or estimates in general. Needless to say, without blinding, an evaluator could also make his comments on the analysis incredibly biased, consciosuly or unconsciously, if he knows the group memberships.

But, how would an evaulator unconsciously select a method that yields larger or smaller p-values, or estimates in general?

You just keep on claiming that he could.

You don't explain how.
 
CFLarsen said:


But, how would an evaulator unconsciously select a method that yields larger or smaller p-values, or estimates in general?

You just keep on claiming that he could.

You don't explain how.

Yes. TC, could you please explain how a someone could select a method that yields larger or smaller p-vaules?

You can either do this or you can't. Please, just pick one.
 
so, let's skip the battle of words and get into the real world we live in....

does it do any good? Is it of any use?

does it cause harm?

If the JE that told my friend all about her dead son had given her any real information, instead of at first getting her dead second cousin....then got her dead dog (from childhood, only she had to tell HIM it was her dog from childhood....I guess dogs in heaven speak English)....then on and on as her friends and family watched in anguish until the ultimate final tragedy...

If he had come up with any real information at first. The guy couldln't even be bothered to go beyond the cold reading. If he had googled her son, he would at least have given her some real information - and maybe it all would have stopped sooner.

So, I don't care if he gets some "hits". I want this to be like any other major scientific breakthrough, something that gets better or can be refined. Something of some real use, not a silly parlour game that gets out of control.

When scientists were first informed of the platypus, they laughed, they said there was no way it could be real. They didn't care who was reporting it, they didn't care about the drawings, it was IMPOSSIBLE. But then, quickly for the tiimes, when one was killed, stuffed and sent to England, and scientists saw it had not been pieced together - they changed their minds. So, change our minds. If it can't be done convincingly then it can be slightly, or even more than slightly dangerous.

I know, I take a lot of flack for NOT being the scientist and going on the same anecdotal evidence that the "woo-woo" crowd uses. Oddly enough, if you look, or have the bad luck to experience it first hand there is a lot of anecdotal evidence to the dangers of cold reading.
 
T'ai Chi said:


Not the issue at all.

For what it is worth, they were for students' Ph.D and M.S. theses (which they did very well on). Your attempt at changing the topic is noted.
Ah, goody. Theses are published, too. Thesis authors follow the same protocol of acknowledging consultants. Give us the student's names, the schools and the years. I know where to look.
 
TLN said:

Yes. TC, could you please explain how a someone could select a method that yields larger or smaller p-vaules?

You can either do this or you can't. Please, just pick one.

You and Claus are asking me to explain how someone uses their brain to select something? Um..

Look, if an evaluator knows deep in his mind that one method generally gives smaller p-values than another method, he might unconsciously tend towards that one (or another one) if he desires to unconsciously support his bias as much as he can.
 
T'ai,

I repeat:

Theses are published, too. Thesis authors follow the same protocol of acknowledging consultants. Give us the student's names, the schools and the years. I know where to look.

Back up your claim.
 
BillHoyt said:
T'ai,

I repeat:

Theses are published, too. Thesis authors follow the same protocol of acknowledging consultants. Give us the student's names, the schools and the years. I know where to look.

Back up your claim.

I'll repeat for you: I won't budge an inch to your extremist prima donna demands.

You'll have to stick to the issues to be taken seriously. You know darn well that my consulting work in school has absolutely nothing to do with the issues at hand, and that the lack of such information will not prevent you from addressing mathematical and statistical issues. You are just latching on to it as a pathetic excuse.

Carry on.
 
BillHoyt said:
T'ai,
I repeat:
(snip)

You first posted your silly demand on 1/31/04 at 12:58AM. Then you posted it again the same day at 7:45AM. You're an impatient one, aren't ya?
 
T'ai Chi said:
You and Claus are asking me to explain how someone uses their brain to select something? Um..

Well, duuuuh....that was your claim that you knew, you know....

T'ai Chi said:
Look, if an evaluator knows deep in his mind that one method generally gives smaller p-values than another method, he might unconsciously tend towards that one (or another one) if he desires to unconsciously support his bias as much as he can.

I think I understand now. The statistician is able to - without doing the analysis consciously - determine what method will give his favored result.

In other words, the statistician has the same autistic abilities as Dustin Hoffman's character in the movie "Rainman".

He doesn't use paranormal powers, he is autistic!!

Hey, I get it now, T'ai Chi. It all makes sense now.

:dl:
 

ISF - Join now!

Every member here is approved by hand. No bots, no spam, just people who care about evidence and honest debate.

Membership is free!

Create your free account

Back
Top Bottom