Merged Odds Standard for Preliminary Test

[Moochie]

I think I have more sympathy for the pro-paranormalists (in general) than you have. I think it's obvious to anyone with the sense of a cucumber that if the paranormal exists, it's a very subtle thing. I can't simply scratch names on onions and see whom I'm going to marry or spin a set of coins to tell me if I will get a better job next year.

It's a claim some people make. Opinion.

But it's also obvious to those same cucumbers that the real world is very subtle; I can't just walk into a pharmacy and grab a drug to make me feel better, which is why medical school takes several years. So it's obvious to any thinking paranormalist (which I admit is a very small group) that demonstrating that the paranormal exists will require a very deft touch and a very sensitive experiment.

A major research project, in fact.

Good luck with that.

The flip side of that is that such projects are expensive to run. I could easily burn through a million bucks in a year testing remote vision. Well, I could , if I had that million bucks -- but the NSF wouldn't touch that proposal with a hayfork. The only group that appears willing to front large amounts of research money for this purpose is the JREF.

The JREF is researching the paranormal? Since when?

Having said that, that's not what the JREF does, and it's no more willing to shell out a million for psychic research than the NSF. But I think people get more upset about their misunderstanding of the JREF than their (true) understanding of the NSF.

Glad you clarified that.

I think Rodney, in particular, is misunderstanding what the JREF does. And it ticks him off that an organization run by a magician is more into showmanship and fraud detection than it is into bench science. Poor thing.

Not sure I agree with that summation.


M.

 

[pavel_do]

...which would of course perfectly illustrate one reason why the MDC was discontinued: It has served its purpose. By attracting people making claims like the one Pavel makes.

Ye ye... this Pavel is such pain in the neck.. cause of him and others a like him. MDC has to be closed down...

 

[drkitten]

Let's suppose the JREF were dumb enough to do that. What would it prove that someone managed to beat 1:100 odds?

The same thing that it proved if she managed to beat 1:10000000000000000000000 odds. That either something strange is going on, or she got really lucky. No statistical test will prove beyond a doubt that the paranormal exists.

The question is whether the risk of Sylvia being able to win (by chance) and walk away with JREF's money and bragging rights is worth the chance of being able to demonstrate with relative firmness that she has no paranormal powers. And that question is both risk-dependent and "not my call to make."

 

[GzuzKryzt]

Ye ye... this Pavel is such pain in the neck.. cause of him and others a like him. MDC has to be closed down...

Obviously, you are no pain in the neck. You might wish, but you aren't.

As obviously, you are a semi-clever self-promoter who will very likely fail the MDC preliminary test and not follow up your wild claims with any substantial evidence.

I dare you to conduct proper research at an established facility. No odds discussion there.

Also: No million dollars for false postive longshot hail mary lucky punch.

 

[fls]

I dare you to conduct proper research at an established facility. No odds discussion there.

I was under the impression that Pavel already had been tested at a psychology department and had submitted those results (along with the affadavits of the researchers) to the JREF as part of the application?

Linda

 

[Rodney]

The same thing that it proved if she managed to beat 1:10000000000000000000000 odds. That either something strange is going on, or she got really lucky.

You really don't see the difference between 1:100 and 1:10000000000000000000000 odds?

No statistical test will prove beyond a doubt that the paranormal exists.

By that logic, no statistical test can prove beyond a doubt that anything exists. In the real world, however, once a phenomenon defies extraordinarily high odds, it is conceded by rational people to exist.

The question is whether the risk of Sylvia being able to win (by chance) and walk away with JREF's money and bragging rights is worth the chance of being able to demonstrate with relative firmness that she has no paranormal powers. And that question is both risk-dependent and "not my call to make."

The problem with that logic is that one test cannot possibly demonstrate that she has no paranormal powers and -- while beating odds of 1:100 by pure luck is unlikely -- it is not at all mind-boggling. Beating odds of at least 1:1000000 would be mind-boggling.

 

[GzuzKryzt]

I was under the impression that Pavel already had been tested at a psychology department and had submitted those results (along with the affadavits of the researchers) to the JREF as part of the application?

Linda

Since the JREF does not publish the content of said affidavits I assume the tests that lead to said conclusions did not meet rigorous controls. I base this assumption on experience with similar situations - not the least of which involved Uri Geller - and I am willing to be convinced otherwise.
However, I would not wish to drain the JREFs resources by submitting tangential inquiries.

By proper research I was first and foremost hinting strongly: Something with no million dollars as a dangling carrot. Only a Nobel Prize.

 

[drkitten]

You really don't see the difference between 1:100 and 1:10000000000000000000000 odds?

You've already demonstrated to my satisfaction that you have no knowledge of statistics. You needn't keep trying.

By that logic, no statistical test can prove beyond a doubt that anything exists.

Got it in one. That's one of the problems of statistics. A null hypothesis can never be proven, and it can never be disproven absolutely.

The problem with that logic is that one test cannot possibly demonstrate that she has no paranormal powers and -- while beating odds of 1:100 by pure luck is unlikely -- it is not at all mind-boggling. Beating odds of at least 1:1000000 would be mind-boggling.

Perhaps -- but that says more about your mind than it does about the world. Lots of people beat odds of 1:1000000. Is your mind boggled by the fact that lottery winners exist?

 

[drkitten]

The problem with that logic is that one test cannot possibly demonstrate that she has no paranormal powers

And here we see Rodney's fundamental problem. He admits that he can never be convinced that Sylvia has no paranormal powers, and he wonders why we won't simply let her adjust the odds until she can win?

 

[Rodney]

You've already demonstrated to my satisfaction that you have no knowledge of statistics. You needn't keep trying.

Feel free to submit this thread to an unbiased statistician and see if s/he thinks your arguments make more sense than mine.

Got it in one. That's one of the problems of statistics. A null hypothesis can never be proven, and it can never be disproven absolutely.

Which is technically true, but meaningless. Science -- and life in general -- is based on statistics, and when the odds become overwhelming enough, rational people accept or reject a hypothesis, instead of arguing something like: "We still don't know for sure whether Tiger Woods is a top golfer. He may just be extraordinarily lucky."

Perhaps -- but that says more about your mind than it does about the world. Lots of people beat odds of 1:1000000. Is your mind boggled by the fact that lottery winners exist?

No, because if there are only 1 million combinations in a lottery and tickets are sold for each of those combinations, it is inevitable that there will be a lottery winner. But that's completely different than a JREF applicant beating odds of one in a million.

 

[drkitten]

Feel free to submit this thread to an unbiased statistician and see if s/he thinks your arguments make more sense than mine.

I have. I work in a university, in very close cooperation with several professional statisticians.

They think, not to put too fine a point on it, that you are ignorant to the point of dishonesty, although they use more professional language.

No, because if there are only 1 million combinations in a lottery and tickets are sold for each of those combinations, it is inevitable that there will be a lottery winner.

I see. So if only 999,999 tickets were sold, then it would be mind-blowing? (Excuse me, mind-boggling.)

But that's completely different than a JREF applicant beating odds of one in a million.

Shall I run this statement by the statisticians as well? It's a slow day and they would probably appreciate how badly they are needed in educating the general public.

 

[Rodney]

I have. I work in a university, in very close cooperation with several professional statisticians.

They think, not to put too fine a point on it, that you are ignorant to the point of dishonesty, although they use more professional language.

So how about a specific critique by them? Better yet, have them join this forum and weigh in here, so everyone can benefit from their wisdom.

I see. So if only 999,999 tickets were sold, then it would be mind-blowing? (Excuse me, mind-boggling.)

If 999,999 different combinations were sold, leaving only 1 that wasn't sold, it would be far more mind-boggling if there were no lottery winner.

Shall I run this statement by the statisticians as well? It's a slow day and they would probably appreciate how badly they are needed in educating the general public.

Bring it on.

 

[petre]

Let's suppose the JREF were dumb enough to do that. What would it prove that someone managed to beat 1:100 odds?

To who, me? That more investigation may be worthwhile? I believe JREF would take the 99:100 odds of showing Sylvia can't even beat a simple test. It would never happen though, Sylvia has far more to lose on that 99:100 side than she could gain on the 1:100 side.

 

[drkitten]

So how about a specific critique by them? Better yet, have them join this forum and weigh in here, so everyone can benefit from their wisdom.

And, once again, the woos insist it is science's job to drop everything and disprove each individual nut-case idea for free.

If you want a professional statistician to critique your ideas, the American Statistical Association maintains a list of consultants; I believe the current rate is around $250/hour. If you have something useful, like an interesting (read: publishable) research project to bring to the table, they may be willing to work for less.

 

[Rodney]

And, once again, the woos insist it is science's job to drop everything and disprove each individual nut-case idea for free.

If you want a professional statistician to critique your ideas, the American Statistical Association maintains a list of consultants; I believe the current rate is around $250/hour. If you have something useful, like an interesting (read: publishable) research project to bring to the table, they may be willing to work for less.

You might try re-reading your previous post (#351 on this thread). I was responding to what you said there.

 

[drkitten]

I was responding to what you said there.

I know. Without thinking, as is usual.

You asked what a professional statistician would think of your "argument." Having shared your illiterate and innumerate rantings with some of my colleagues, I am in a position to answer you -- they think you're an idiot, an opinion they volunteered over the coffee pot.

You then asked for a "specific critique." If you want a consultancy report, consultancy cost money. They're busy professionals and have requests for critiques piling up on their desks; in fact, consultancy is a major supplement to their faculty salaries. But if you want a professional statistician to explain type I and type II errors to you (and how no statistical study can be entirely free of either type, and how the threshholds are set by the study designer based on externallities like percieved risk), I'm sure you can find one.

In fact, I even gave you the name of the relevant professional organization from which you can try to hire one. But, as I warned you, an hour's consultation will typically cost around $250.

 

[Rodney]

I know. Without thinking, as is usual.

You asked what a professional statistician would think of your "argument." Having shared your illiterate and innumerate rantings with some of my colleagues, I am in a position to answer you -- they think you're an idiot, an opinion they volunteered over the coffee pot.

You then asked for a "specific critique." If you want a consultancy report, consultancy cost money. They're busy professionals and have requests for critiques piling up on their desks; in fact, consultancy is a major supplement to their faculty salaries. But if you want a professional statistician to explain type I and type II errors to you (and how no statistical study can be entirely free of either type, and how the threshholds are set by the study designer based on externallities like percieved risk), I'm sure you can find one.

In fact, I even gave you the name of the relevant professional organization from which you can try to hire one. But, as I warned you, an hour's consultation will typically cost around $250.

Before I pay even 25 cents, I would want to know whether the consultant believes -- as you evidently do -- that there is still some uncertainty about things that are obvious even to people who have never taken a statistics course -- such as whether Tiger Woods is a top golfer.

In any event, the subject of this thread is "Odds Standard for Preliminary Test", and it's rather obvious to anyone who has been reading that the JREF does not have a consistent position on that subject.

 

[drkitten]

Before I pay even 25 cents, I would want to know whether the consultant believes -- as you evidently do -- that there is still some uncertainty about things that are obvious even to people who have never taken a statistics course -- such as whether Tiger Woods is a top golfer.

Then you'll never find a consultant to pay, because any qualified statistician will point out that every statistical test involves non-zero alpha and beta cutoffs, and thus there is uncertainty involved.

In fact, you don't even need to get the professionals involved for that one. Anyone who took and passed baby stats can give you the same answer for a lot less money.

In any event, the subject of this thread is "Odds Standard for Preliminary Test", and it's rather obvious to anyone who has been reading that the JREF does not have a consistent position on that subject.

On the contrary, they have a very consistent position on that subject. Their position --- forthrightly stated --- is that there are no standards and that odds are negotiated on a case-by-case basis.

Has it really taken you nearly four hundred posts before you realized that the JREF are serious about that?

 

[EHocking]

Has Will it really taken you nearly over four hundred posts before you realized that the JREF are serious about that?

Small correction that I think better reflects his position.

 

[Moochie]

<snip>



In any event, the subject of this thread is "Odds Standard for Preliminary Test", and it's rather obvious to anyone who has been reading that the JREF does not have a consistent position on that subject.

And the reasons for that have been explained to you.


M.