Cold Reading Demos at TAM2

T'ai Chi,

Back up a bit here. If I have not understood what you are saying, then let's get that cleared up now.



We have one dataset (A) that comes from the "paranormal" group.

We have one dataset (B) that comes from the "normal" group.

The statistician knows which group is which.

The statistician uses the same method on (A) and (B).

A method that the statistician knows - before he analyses the data - will give a result that favors the "paranormal" group.



That is what you are saying, right?
 
T'ai Chi said:


Yes, avoiding like the plague Jeff, because I've already mentioned the revised (ie. error free) Fisher's Exact vs. Chi square situation more than several times now, and yet you still seem to want to harp on the error for some reason.

Why is that?
Jeff was talking about your use of 2-tail on the one hand and 1-tail on the other hand. Now you start talking about your feet. Stop displaying your ignorance and diverting from the topic, sir.

But since you keep harping on Fisher, I thought you ought to know this little tidbit about it:

"NOTE: Decide to use Left, Right or 2-Tail before collecting (or looking at) the data." Getting hit over the head lessons

So, with your own example test, now you are back to the choice outlined before. You are either talking about your very confused statistician/evaluator/principal researcher deterimining a priori which test will give him results he wants or deterimining it a posteriori. If a priori, you are claiming a paranormal situation. If a posteriori, you are committing scientific fraud.
 
CFLarsen said:

I have not "put faith" in what he says. Please provide evidence that I have.
Typical Claus. Avoid the question by focussing on tangents. It is simple. Do you believe Hoyt or not? Nothing I have seen you post would indicate that you are the least bit skeptical when it comes to his posts.

Are you ever going to address the example I posted, or are you just going to keep dodging?

Frankly, I don't care what you think T'ai Chi is claiming. I care about what he actually is claiming.
No you don't, as he has told you repeatedly what he is actually claiming and you ignore it in favour of your twisted interpretations. I think you only care about harrassing T'ai Chi (as well as vertain other posters).

I am not playing favourites here. I am questioning T'ai Chi's credentials. First things first.
And that isn't playing favourites. Riiight. :rolleyes:


Not correct. Please do not tell me what I meant.
BS. I am correct. This is what you said:
Oh, I understand bias very well. What I also understand is that, for your explanation to work, your statistician need to be autistic. Not have supernatural powers, just autistic.
Does this not imply that either:

(a) All autistic people have super calculating abilities; or
(b) in order to have super calculating abilities, one must be autistic?

That is exactly what you said. There is no third option. I notice that while denying that I am correct, you don't actually point out what you say you meant. Interesting.
 
Another issue is all this talk about "unconscious " bias. How can we tell if a bias is unconscious or not? The whole conscious/unconscious issue is problematical.
And statisticians are also subject to public scrutiny. Given that the data published in a peer reviewed journal can be analyzed by anybody with a couple of stat courses, just like I analyzed TC's data and found his huge error, why would someone risk their rep by being careless (as TC was) or by cheating?
 
Thanz said:
Typical Claus. Avoid the question by focussing on tangents. It is simple. Do you believe Hoyt or not? Nothing I have seen you post would indicate that you are the least bit skeptical when it comes to his posts.

It is simple: I do not put "faith" in Hoyt's post.

Thanz said:
Are you ever going to address the example I posted, or are you just going to keep dodging?

What example did you post?

Thanz said:
No you don't, as he has told you repeatedly what he is actually claiming and you ignore it in favour of your twisted interpretations. I think you only care about harrassing T'ai Chi (as well as vertain other posters).

If you think I only care about harrassing people here, then I must insist that you report me to the moderators.

I have asked T'ai Chi for clarification. Let's see what he replies.

Thanz said:
And that isn't playing favourites. Riiight. :rolleyes:

No, it is about taking care of things in the order they appear.

Thanz said:
That is exactly what you said. There is no third option. I notice that while denying that I am correct, you don't actually point out what you say you meant. Interesting.

I have addressed it. I admitted my error. I should have used "idiot savant".

You know this, yet you keep claiming that I still claim "autism".

I am not going to shriek "harrassment" as you seem highly prone to do. I am merely pointing it out.
 
CFLarsen said:

What example did you post?
Hoyt's "J" analysis. Bottom of page 10 of this thread.

If you think I only care about harrassing people here, then I must insist that you report me to the moderators.
My opinion is that you revel in harassing certain posters. I do not think that your behaviour is outside of the forum rules - I just think that it is not civilized behaviour. If you want to act that way (and it is clear that you do) it is not up to me to stop you. All I can do is point it out and express my opinion - which I have done.

I have addressed it. I admitted my error. I should have used "idiot savant".

You know this, yet you keep claiming that I still claim "autism".
Dude, just let it lie. Look back over the actual statements that were made, and what I was actually responding to. Maybe then you will understand.

I am not going to shriek "harrassment" as you seem highly prone to do. I am merely pointing it out.
I am not "shrieking", I am merely pointing things out. I have not reported you to any moderators. I am not the schoolkid running to the teacher. I am posting my opinion of your posting habits. If YOU can't handle that, why don't you report me?
 
Jeff Corey said:
Another issue is all this talk about "unconscious " bias. How can we tell if a bias is unconscious or not? The whole conscious/unconscious issue is problematical.
And statisticians are also subject to public scrutiny. Given that the data published in a peer reviewed journal can be analyzed by anybody with a couple of stat courses, just like I analyzed TC's data and found his huge error, why would someone risk their rep by being careless (as TC was) or by cheating?
I think that this points to more "unconscious" bias than "conscious" bias. By its nature, unconscious bias would not be overtly known to the evaluator. It may just guide their analysis, without them knowing that there is a bias influence.

For example, if the white guy hiring a new employee chooses the white guy over the black guy (equally qualified), it is possible that there is an unconscious bias at work (but not definite). Such a decision maker would not think that they are putting any reputation on the line. However, if the guy is a card carrying member of the KKK, that would be a conscious bias.

Anyway, what I am trying to say is that if an analysis was the "victim" of an unconscious bias, one would hope that peer review would either correct the errors or at least posit an alternative analysis. Such a person would not think that they are putting a rep on the line, as they think that the analysis is objectively correct. So, if you believe in the basic "goodness" of people, you may be able to assume that bias is unconscious until you are given reason to believe it may be conscious.
 
Thanz said:
Hoyt's "J" analysis. Bottom of page 10 of this thread.

Please point to the original thread where this is discussed.

Thanz said:
My opinion is that you revel in harassing certain posters. I do not think that your behaviour is outside of the forum rules - I just think that it is not civilized behaviour. If you want to act that way (and it is clear that you do) it is not up to me to stop you. All I can do is point it out and express my opinion - which I have done.

No, no: Harrassment is harrassment. I don't see any graduation of that term in the rules.

Thanz said:
Dude, just let it lie. Look back over the actual statements that were made, and what I was actually responding to. Maybe then you will understand.

Oh, I understand perfectly. You can't admit to your error.

Thanz said:
I am not "shrieking", I am merely pointing things out. I have not reported you to any moderators. I am not the schoolkid running to the teacher. I am posting my opinion of your posting habits. If YOU can't handle that, why don't you report me?

Why don't you read what I write?

I said I did not call it harrassment, I merely pointed out that you tried to attribute me with something you knew I had already admitted was an error.
 
Very briefly (since I'm teaching right now) I'd say that Bill's method was a bit strange (not that I'm qualified in stats or maths or anything like that) but when I followed the more accepted method of counting, I still got results that strongly pointed to cold reading.

There've been more transcripts come to light since then (JE has appeared at least six times on LKL). It may be worth having another look and doing more sums.
 
Ersby said:
Very briefly (since I'm teaching right now) I'd say that Bill's method was a bit strange (not that I'm qualified in stats or maths or anything like that) but when I followed the more accepted method of counting, I still got results that strongly pointed to cold reading.
I think that all of the counts showed a higher than average number of J guesses, which could be said to "strongly point to cold reading". However, only the count done by Hoyt met the statistical significance test he proposed (that is, only his count would reject the null hypothesis). Other counts could not reject the null hypothesis.

For the record, I also think that JE is cold reading. I just don't think that this analysis proves that.
 
Thanz said:
It was in the massive thread The "Process" of John Edward

Thank you for wasting my time pointing to the wrong page. I would prefer it if I did not have to wade through 28 pages to find your examples.

I see Hoyt explain statistics. Not necessarily the clearest explanation I have ever seen. But he does try.

I see Lurker try to understand. Not the easiest task. But he does try.

I see T'ai Chi try to counter Hoyt, but is rebutted by Jeff Corey.

I see you do a Google and think you can participate in a discussion on statistics.

If I have missed something relevant (I frankly don't have time to read closely through 28 pages), you are most welcome to point it out.

Now, to your post in this thread:

Thanz said:
Let's take Mr. Hoyt as an example. Some time ago there was a thread in which the letter J was analyzed for frequency against the general population. Mr. Hoyt chose a Poisson distribution test, but never explained why it was appropriate for the analysis. But let's just take his test as appropriate.

Fine with me.

Thanz said:
He then embarked on a counting method of J's that defied logic and came up with a statistically significant result, using the Poisson test. When anybody else used the same raw data and went through counting guesses and letter J's, the results were not statistically significant.

Really? Where do people show this? (and, please be precise!)

Thanz said:
So, did Mr. Hoyt consciously choose a method to skew the results in his favour? If he did, he is intellectually dishonest and a fraudster.

Did he unconsciously choose a method that would skew the results in his favour? If that is what happened, then you have a great example of bias on the statisticians part altering the results.

First, I have not seen your evidence that Hoyt consciously chose a method that skewed the results in his favor.

Second, this example is not comparable to T'ai Chi's: T'ai Chi is (presumably!) talking about two sets of data, where the same method is being applied, and the result favors the "paranormal" dataset.

That's what I am trying to get T'ai Chi to explain. I try to keep focused here.

So, whatever your beef with Hoyt is, take it up with him.
 
CFLarsen said:


Thank you for wasting my time pointing to the wrong page. I would prefer it if I did not have to wade through 28 pages to find your examples.
My example is in this thread, and does not require an indepth analysis of the other thread. Nevertheless, you asked for the thread, and I gave it to you. Page one. I wasn't going to wade through it either when I don't know why you needed to see it.

If I have missed something relevant (I frankly don't have time to read closely through 28 pages), you are most welcome to point it out.
Well, how about the fact that no one agrees with the method that Bill chose? That seems fairly relevant to the issue of possible bias on the part of Mr. Hoyt.

Really? Where do people show this? (and, please be precise!)
Sure. I point it out on page 19, near the middle, posts on 8/25/03 at 11:02 and 11:58. Walter Wayne on Page 21, bottom, 8/31/03, 1:33 am

The discussion of counting methods goes on for several pages, and is marked by Mr. Hoyt avoiding several direct questions in favour of making snarky remarks.

First, I have not seen your evidence that Hoyt consciously chose a method that skewed the results in his favor.
I am not claiming that he necessarily consciously chose a biased method. I am saying that he did in fact choose a method that gave him results that were biased in his position's favour. If it was a conscious choice, it was fraudulent. If it wasn't, then I am using it as an example of unconscious bias. Get it?
 
Thanz said:
My example is in this thread, and does not require an indepth analysis of the other thread. Nevertheless, you asked for the thread, and I gave it to you. Page one. I wasn't going to wade through it either when I don't know why you needed to see it.

You really don't think that I should check what was actually said, but that I should rely entirely on your account?

Dream on, Thanz!

Thanz said:
Well, how about the fact that no one agrees with the method that Bill chose? That seems fairly relevant to the issue of possible bias on the part of Mr. Hoyt.

Not correct. Check Jeff Corey. See why I ask to see the sources?

Thanz said:
Sure. I point it out on page 19, near the middle, posts on 8/25/03 at 11:02 and 11:58. Walter Wayne on Page 21, bottom, 8/31/03, 1:33 am

The discussion of counting methods goes on for several pages, and is marked by Mr. Hoyt avoiding several direct questions in favour of making snarky remarks.

How far do I have to read, Thanz? The remaining 9 pages, seeking out the information myself?

Thanz said:
I am not claiming that he necessarily consciously chose a biased method. I am saying that he did in fact choose a method that gave him results that were biased in his position's favour. If it was a conscious choice, it was fraudulent. If it wasn't, then I am using it as an example of unconscious bias. Get it?

No, you have not shown that it gave him the results he wanted. Perhaps you could show me - pointing to statistic methods - where he is wrong?

That is by far easier than me reading 28 pages trying to find out what you mean. It should also be easier for you, since you understand the issue in depth.

If you cannot, then I have to leave you with it. You are not making a very compelling case (you even misrepresent what actually happened), and I have better things to do than cater to your problems with Hoyt.
 
CFLarsen said:


You really don't think that I should check what was actually said, but that I should rely entirely on your account?

Dream on, Thanz!
I am not here to spoon feed you. I have given you the appropriate references. Frickin read them.

Not correct. Check Jeff Corey. See why I ask to see the sources?
Now I have to ask you for some precision. Where is the post where Jeff Corey agrees with Hoyt's counting method?

How far do I have to read, Thanz? The remaining 9 pages, seeking out the information myself?
It would help if I knew what precise information you want.

No, you have not shown that it gave him the results he wanted. Perhaps you could show me - pointing to statistic methods - where he is wrong?
See my post at the top of page 26 of that thread. It contains 2 previous posts ignored by Mr. Hoyt. I point out with specific examples why his counting method is not logical.

If you cannot, then I have to leave you with it. You are not making a very compelling case (you even misrepresent what actually happened), and I have better things to do than cater to your problems with Hoyt.
I must ask you to clarify what you claim the misrepresentation is.
 
Thanz said:
I am not here to spoon feed you. I have given you the appropriate references. Frickin read them.

If you want to point to references, you do not point to a 28-page thread with more than a thousand posts that will take days to read. That is as ridiculous as Steve Grenard telling people to do a Google.

Thanz said:
Now I have to ask you for some precision. Where is the post where Jeff Corey agrees with Hoyt's counting method?

Who said anything about a counting method? You asked about the statistical method, not the counting method.

Sorry, Thanz, but I am fed up with your dishonesty.

Thanz said:
It would help if I knew what precise information you want.

Huh?? I am asking you to back up your claims, and you ask me for information?

Thanz said:
See my post at the top of page 26 of that thread. It contains 2 previous posts ignored by Mr. Hoyt. I point out with specific examples why his counting method is not logical.

Another reference. They seem to come dripping. I've asked you to collate the posts you want me to address, instead of this very confusing presentation. You refuse.

Thanz said:
I must ask you to clarify what you claim the misrepresentation is.

I will not play your games. You are dishonest, you change your claims, you misrepresent.

You have also completely ignored my asking for you to show me - pointing to statistic methods - where Hoyt is wrong. I know that you are not stupid, so I have to assume that you refuse. You just think nobody would notice.

I do not have more time for you and your beef with Hoyt.
 
CFLarsen said:

If you want to point to references, you do not point to a 28-page thread with more than a thousand posts that will take days to read. That is as ridiculous as Steve Grenard telling people to do a Google.
This from the guy who pointed to a zip file of all of the posts for a certain period of time at tvtalkshows as evidence for his claims, without any specificity at all. That is right. I am really sick of your continual BS, Mr. Larsen.

Who said anything about a counting method? You asked about the statistical method, not the counting method.

Sorry, Thanz, but I am fed up with your dishonesty.
You can take this and with it perform the anatomical impossibility of your choice. Here is my original example, from this thread:

Let's take Mr. Hoyt as an example. Some time ago there was a thread in which the letter J was analyzed for frequency against the general population. Mr. Hoyt chose a Poisson distribution test, but never explained why it was appropriate for the analysis. But let's just take his test as appropriate.

He then embarked on a counting method of J's that defied logic and came up with a statistically significant result, using the Poisson test. When anybody else used the same raw data and went through counting guesses and letter J's, the results were not statistically significant.

So, did Mr. Hoyt consciously choose a method to skew the results in his favour? If he did, he is intellectually dishonest and a fraudster.

Did he unconsciously choose a method that would skew the results in his favour? If that is what happened, then you have a great example of bias on the statisticians part altering the results.
Don't tell me you did not know I was talking about his counting method. You are either profoundly ignorant, or deliberately lying.

Huh?? I am asking you to back up your claims, and you ask me for information?
I have backed up my claims. I pointed you to the thread. I pointed you to specific posts in that thread. That is called backing up my claim. It's not my fault if you refuse to read it and understand.

Another reference. They seem to come dripping. I've asked you to collate the posts you want me to address, instead of this very confusing presentation. You refuse.
Let's get this straight. I point you to a thread, you get upset. I point you to specific posts in the thread, you still get upset. If you had read the frickin post I pointed you to, you would see that it summarizes my arguments quite well. But of course you won't do that, because you just want to continue this farce. You refuse to address any issues, and just spewe tangents from your computer.

I do not need to summarize the thread. The posts are there for you to see. The post I pointed you to is in itself a summary. Read it there.

I will not play your games. You are dishonest, you change your claims, you misrepresent.
I have not changed my claims. Point out where I have changed my claims. Point out any misrepresentations, if you can.

You have also completely ignored my asking for you to show me - pointing to statistic methods - where Hoyt is wrong. I know that you are not stupid, so I have to assume that you refuse. You just think nobody would notice.
I pointed you to the frickin post already. Read the frickin post before you accuse me of not explaining why Hoyt is wrong.

All of this and you have yet to actually address the example. Either address or admit you cannot. Classic Larsen - cling to whatever trumped up BS you can to avoid actually answering any questions.
 
...and still you are not able to show - by pointing to statistic methods - where Hoyt is wrong. A simple request, crucial to your claim.

But, no.

"Empty barrels make the most noise".
Danish proverb.
 
CFLarsen said:
...and still you are not able to show - by pointing to statistic methods - where Hoyt is wrong. A simple request, crucial to your claim.

But, no.
Yes, I have. Look at page 26 of the thread - the first post by me neatly summarizes the problems with his method.

Basically, he counts "I'm getting a J connection, like John or James" as three guesses - as if he had said "J, like J or J" in one reading or "J" connection once in three separate readings. This is an inaccurate count of both the number of J guesses and the total number of guesses. You cannot get a reliable result from flawed data.
 

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