Cold Reading Demos at TAM2

T'ai Chi said:
LOL, it depends on specifics of the experiment. Because there are many ways to analyze data, he could choose different model, a different analysis strategy, different software, different graphical methods, and/or be 'nice' in his commentary on the analysis. The specifics of these, of course, depend on the specifics of the experiment and the data structure.

You still haven't answered the question: How can a statistician - and you can choose whatever specifics of the experiment you like - unconsciously choose the method that gives better results for one group?

T'ai Chi said:
I also didn't say that a statistician's worked cannot be checked as you try to imply. In response to your question "How will his bias not show up when his analysis is checked by someone else?" I said: "Maybe, maybe not." People could just check the calculations, people could already be consciously or unconsciously biased themselves, and a whole host of other possibilities.

We are talking about calculations here, T'ai Chi. Math. How can you interpret a number or a calculation?


T'ai Chi said:
Nope. Statisticians do a lot more than crunch numbers. Despite beliefs otherwise, there is a lot of interpretation that can occur. For example, even if some things are chosen before the experiment even begins, some things might not be. What comes to mind right away are graphical methods, and most obviously, commentary upon the analysis.

But we are not talking about that here. Please stick to your own example!

T'ai Chi said:
I merely claim that the statistican has a lot of things at his disposal for analyzing data, and as with any person, conscious, but mostly unconscious bias can creep in, which is why triple blinding seems to be a pretty good idea.

Not in your own example. Stick to that, instead of desperately looking for ways to get out of the mess you got yourself into.

T'ai Chi said:
It was already mentioned that my example was to show how group membership can be blinded from the evaluator. I really can keep pasting this all day Claus.

You have still not answered the questions. I take it, therefore, that you cannot.

Which brings us all the way back to your claim that you could explain what "tripleblind" was. You can't.

Next time, just admit that you goofed. It saves time, and the egg on your face.
 
CFLarsen said:



Next time, just admit that you goofed. It saves time, and the egg on your face.

In fact, the yoke's on you and lil' Bill. Or is that the drool of a mad-man on your chin?

Why don't cold readers replicate what JE does under the same conditions and controls of scientific research at the HESL?
 
Lucianarchy said:
Why don't cold readers replicate what JE does under the same conditions and controls of scientific research at the HESL?

If they could, what would you say?
 
CFLarsen said:

You still haven't answered the question: How can a statistician - and you can choose whatever specifics of the experiment you like - unconsciously choose the method that gives better results for one group?


Yes, I have. See last post. You may not like the answer, but that isn't my issue.


We are talking about calculations here, T'ai Chi. Math. How can you interpret a number or a calculation?


If I calculate a p-value to be (WARNING CLAUS! This number is totally made up!!!!) .000234 and just leave it as that, I'd get marked down in any statistics class. You have to interpret the p-value. What does the number mean? It means that, in this case, there is a statistically significant difference in the blood pressures of coffee drinkers vs. non-coffee drinkers at the .01 level. Then I'd give a confidence interval for the difference, and offer my suggestions about this, suggestions for future studies, etc.


But we are not talking about that here. Please stick to your own example!


Sorry Claus, my example was to show how group membership could be blinded. I will not (ever) heed by your attempted rule that I cannot talk about what statisticans do in real life, for Pete's sake.


Not in your own example. Stick to that, instead of desperately looking for ways to get out of the mess you got yourself into.


See above.


You have still not answered the questions. I take it, therefore, that you cannot.


See above. I take it, therefore, that you see above.


Which brings us all the way back to your claim that you could explain what "tripleblind" was. You can't.


LOL. I explained that it was to hide the group membership information from the evaluator as to help prevent possible conscious or unconscious bias from creeping in. As I've told you, I really can paste this all day.


Next time, just admit that you goofed. It saves time, and the egg on your face.


Wrong again.
 
CFLarsen said:


If they could, what would you say?

Then I'd say that they could. But to date, they can't,
despite being given the opportunity to do so. I believe
even IR turned down such a golden opportunity. After
all the claims from the pseudo-skeptics, you'd think they'd
be beating a path to the University of Arizona. Yet the path
is paved with nought but crickets.

*chirp*
 
BillHoyt said:

You claimed the statistician could make those decisions after the data are collected. This violates one of the cardinal rules of experimental design. You know that, right?

The evaluators can make many decisions after the data are collected. You know that, right?

Which graph do I use? Should I use this t-test or that t-test? Which computer package? Hmm, how should I interpret these numbers I'm getting? What should my suggestions for future experiments be? How do I relate this to past, current, or upcoming research? What words do I use to record my thoughts? Etc. Not to mention the model(s) might not be specified or specified entirely before the experiment. Ideally, yes, we'd like it to be, but again, like Fisher's quotes, it doesn't always happen. :)
 
Lucianarchy said:
Then I'd say that they could. But to date, they can't,
despite being given the opportunity to do so. I believe
even IR turned down such a golden opportunity. After
all the claims from the pseudo-skeptics, you'd think they'd
be beating a path to the University of Arizona. Yet the path
is paved with nought but crickets.

*chirp*

Yes, that's nice. But, what would it prove? What would be the consequences, Lucianarchy?

Where would that leave the psychics?
 
T'ai Chi said:


The evaluators can make many decisions after the data are collected. You know that, right?

Which graph do I use? Should I use this t-test or that t-test? Which computer package? Hmm, how should I interpret these numbers I'm getting? What should my suggestions for future experiments be? How do I relate this to past, current, or upcoming research? What words do I use to record my thoughts? Etc.

Would either of these choices influence - unconsciously - the results?

You keep dodging this.
 
CFLarsen said:

Yes, that's nice. But, what would it prove?


Hard to say. But if people claim it is so easy etc., I admit that while I don't agree with a lot of Schwartz's conclusions or experiment, I do think that it is interesting that no one seems to be conclusively showing their skills in an experimental setting.
 
CFLarsen said:

Would either of these choices influence - unconsciously - the results?


You mean would any of these choices, as I presented many possible options.

They could influence the results or the way the results are looked at, yes. It is possible since everyone has bias, hence the strong need for blinding in the first place.


You keep dodging this.

Wrong.
 
T'ai Chi said:
Hard to say. But if people claim it is so easy etc., I admit that while I don't agree with a lot of Schwartz's conclusions or experiment, I do think that it is interesting that no one seems to be conclusively showing their skills in an experimental setting.

If there are no consequences if they did, then there is not much idea in trying, is there?

Surely, you don't consider Schwartz' experiments as scientifically sound?

If you do, please explain why.

If you don't, which scientists have performed scientifically sound experiments of psychics?
 
T'ai Chi said:
You mean would any of these choices, as I presented many possible options.

They could influence the results or the way the results are looked at, yes. It is possible since everyone has bias, hence the strong need for blinding in the first place.

How? You just state that they could. Please explain how.

How would these choices influence - unconsciously - the results?

T'ai Chi said:

Sorry, but your own posts show this to be true.
 
CFLarsen said:


Yes, that's nice. But, what would it prove? What would be the consequences, Lucianarchy?

Where would that leave the psychics?

What would, what would, what would..

Claus, these are the questions for a hypothesis. You could test it easily by getting a cr to accept the Research Chair Challenge.

ITMT, you have accept the fact that JE will perform under the research of Dr Schwartz and the cr's have to date failed to replicate those results, despite being given the opportunity.
 
Claus, these are the questions for a hypothesis. You could test it easily by getting a cr to accept the Research Chair Challenge.

Why play in a game rigged against you? Schwartz refuses to disclose all the data of his experiments before, why should anyone believe that Schwartz would allow all the data to be released in his "challenge"?

In short, Schwartz has very little credibility, that's why cold-readers haven't taken him up on his challenge.
 
Lucianarchy said:
What would, what would, what would..

Claus, these are the questions for a hypothesis. You could test it easily by getting a cr to accept the Research Chair Challenge.

But why would you test it? What would the consequences be, Lucianarchy? Come, now, let's hear it. There's not much point in performing such a test, if the result meant nothing.

Lucianarchy said:
ITMT, you have accept the fact that JE will perform under the research of Dr Schwartz and the cr's have to date failed to replicate those results, despite being given the opportunity.

Male bovine manure. What would the consequences be, Lucianarchy?
 
thaiboxerken said:
Claus, these are the questions for a hypothesis. You could test it easily by getting a cr to accept the Research Chair Challenge.

Why play in a game rigged against you? Schwartz refuses to disclose all the data of his experiments before, why should anyone believe that Schwartz would allow all the data to be released in his "challenge"?

In short, Schwartz has very little credibility, that's why cold-readers haven't taken him up on his challenge.

Name these cold readers who have not taken the challenge because they claim it is "rigged". :confused: You are making things up now. Are you nuts!?

like the JREF, the applicant comes to the challenger. Although I believe that Dr Schwartz would asist and accomodate some people in order to get them there.
 
Name these cold readers who have not taken the challenge because they claim it is "rigged". :confused: You are making things up now. Are you nuts!?

No, I'm not nuts, psychic-boy, I'm just stating the obvious. Skeptics have criticised Schwartz' methods, now Schwartz want to challenge skeptics with those same methods.


like the JREF, the applicant comes to the challenger. Although I believe that Dr Schwartz would asist and accomodate some people in order to get them there.


Garrette keeps trying, it seems that Schwartz isn't accomodating.
 
No, I'm not nuts, psychic-boy, I'm just stating the obvious. Skeptics have criticised Schwartz' methods, now Schwartz want to challenge skeptics with those same methods.

Skeptics just don't understand science like Schwartz. They doubted DaVinchy, now they are doubting Schwartz. Schwartz has evidence of the afterlife, and skeptics are just too scared to admit it.



Garrette keeps trying, it seems that Schwartz isn't accomodating.


I don't know who this Garrette guy is, but he's probably just making up stuff. It's typical of skeptics to lie about such things.
 
T'ai Chi said:
The evaluators can make many decisions after the data are collected. You know that, right?
Yes.
Which graph do I use?
Has nothing to do with the hypothesis test, sir. This is a presentational decision.
Should I use this t-test or that t-test?
No, they can't. This is an a priori decision. That is why Fisher says the statistician should have been there from the beginning. You clearly have no idea what you are talking about with regard to statistics, you poser! Power, sir, depends on the type of test and n. That is why Fisher said what he said. Your sig line, clearly, was disingenuously chosen to help your pitiful pose. You had no freakin' idea what Fisher was talking about, tr'oll
Which computer package?
Each choice ought to yield the same results, sir.
Hmm, how should I interpret these numbers I'm getting?
Not with regard to the hypothesis being tested. That is decided a priori. When one writes a research proposal, one needs to spell out possible results of the study up front and discuss in the proposal how that would be interpreted. Follow-on interpretation is relegated to the spinning of hypotheses for future studies, as you mentioned.
How do I relate this to past, current, or upcoming research?
Past and current belong in the background section, and have nothing to do with the hypothesis under test, except as to the formation of the hypothesis. Future is in the discussion section, and relates to the results of the hypothesis test. Neither have a bearing on the results of the hypothesis under test.
What words do I use to record my thoughts? Etc.
Struggling for red herrings, tr'oll?
Not to mention the model(s) might not be specified or specified entirely before the experiment. Ideally, yes, we'd like it to be, but again, like Fisher's quotes, it doesn't always happen. :)
Wrong, poser. Absolutely wrong. You would be lying about the significance of the test.

T'ai, you have just clearly demonstrated that a) you are no statistician, b) you have been posing for months here, c) you have never studied experimental design, d) you have no understanding of p-value, e) no understanding of "power" in statistics and f) no understanding of blinding. This is pathetic. If you would like to understand these topics, there are several here who could help you, but this sophomoric posing has got to end. You will have to stop these disingenuous posts. You will have to do the hard work of understanding statistics at a far deeper level than you currently do. But if you can't play with the big dogs, just sit and piddle on the porch.
 
Sorry, didn't see this before now.

T'ai Chi said:
Yes, I have. See last post. You may not like the answer, but that isn't my issue.

No, you have not. You have merely repeated your claim.

T'ai Chi said:
If I calculate a p-value to be (WARNING CLAUS! This number is totally made up!!!!) .000234 and just leave it as that, I'd get marked down in any statistics class. You have to interpret the p-value. What does the number mean? It means that, in this case, there is a statistically significant difference in the blood pressures of coffee drinkers vs. non-coffee drinkers at the .01 level. Then I'd give a confidence interval for the difference, and offer my suggestions about this, suggestions for future studies, etc.

But you haven't explained how the statistician unconsciously chooses the method that will give better results for one group.

T'ai Chi said:
Sorry Claus, my example was to show how group membership could be blinded. I will not (ever) heed by your attempted rule that I cannot talk about what statisticans do in real life, for Pete's sake.

I am not saying you can't (ever). I am merely pointing out that your explanation does nothing to explain how a statistician can unconsciously choose the method that gives better results for one group.

T'ai Chi said:
See above.

Evasion noted.

T'ai Chi said:
See above. I take it, therefore, that you see above.

Evasion noted.

T'ai Chi said:
LOL. I explained that it was to hide the group membership information from the evaluator as to help prevent possible conscious or unconscious bias from creeping in. As I've told you, I really can paste this all day.

And I can continue to ask you how a statistician can - and you can choose whatever specifics of the experiment you like - unconsciously choose the method that gives better results for one group. How, T'ai Chi?

Your answer is pivotal to your claim that you can explain what "tripleblind" is and how it works. So far, you have not been able to answer that.

T'ai Chi said:
Wrong again.

Oh, no. Your own posts prove this.
 

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