Micro results in a macro world

[juryjone]

OK, now that I’ve finally topped 100 posts, I suppose it’s time I started a serious topic. It’s one I’ve had floating around in my head for months now – in fact, since I started lurking here about a year and a half ago – but I’m finally taking the time to bring all the disparate thoughts together. I’m afraid I’m going to have to put this serious topic in Banter, since it touches on things from so many other forums. I can only hope this won't be one of those "0 replies" threads.

The question I have in regard to paranormal activities, religion, philosophy etc. is: What good are micro results in a macro world?

THE PARANORMAL
Let’s touch on the paranormal first. How about starting with the PEAR experiments that were debated ad nauseam here months ago? They found that, once you whip all the numbers together, there could be a slighter greater result than chance that a random number generator could be influenced in a general direction (i.e., more ones than zeros generated or vice versa). Even if the results could be replicated repeatedly, of what significance is this? Is this of any practical use? “Oh my god, they’ve released a psychic who can make our RNGs slightly less random! Run for the hills!” Yet it seems that this is the best study that there is to offer.

We’ve all seen dowsers ripped apart in these forums. What can one say when a dowser for gold is thrown off the scent of a hunk of gold in this room by the gold leaf on a book in the next room? Gold teeth/caps/fillings must really throw them off. So, once again, no practical value since they can’t produce the talent at will.

JE, SB and all other people who “speak to the dead” – as many others have stated, where is the practical knowledge? Believers are constantly telling about the wonderful “hits” that have been gotten – yet every one of those hits is something that already happened. “You went to Niagra Falls and picked up a feather that was significant to you.” Hey, tell me something I don’t know. Tell me about what’s going to happen to me in the same detail that you’ve “told” me about my past life. Tell me if I’m going to lose my job, and if I’ll be able to find a new one quickly. Tell me if my wife is thinking of divorce. Tell me if my kid’s taking drugs – if so, what kind and where can I find his stash? Throw me a bone here – give me something I can use, not “He still loves you.” I know a platitude when I hear one. (By the way, the same applies to near-death experiences. Why don’t these people ever come back with any practical news from the beyond? If there is actually an afterlife, why doesn’t everyone who is near death experience something? We get nothing of value in our lives from NDEs, either.)

What have aliens done for us lately? Sure, they built the pyramids for us (using methods that look exactly like they were done by slave human labor), but I gotta say those crop circles mean nothing to me. Amazing how these “signals” have been sent out for years and we haven’t had a single verifiable alien landing. If the signals are for the future, why the hell are they carving them into semi-annual crops? Need a beacon to guide you home from your cross-continental trip? Light a candle! I’d also be more likely to believe in otherwordly intelligent life if, when they came to study our society, they picked out people who actually participate in our society, rather than farmers who live miles from their nearest neighbor.

ALTERNTIVE MEDICINES
There is one way to separate alternative medicines from the real thing – will it work on someone who doesn’t believe in it? If I get a measles vaccine, then run into someone with measles three months later, it’s not going to matter whether I believe in vaccines or not – I will not get measles. Can the same be said for acupuncture, psychic surgery, homeopathy, applied kinesiology, magnets, Q-Ray bracelets, etc., etc., etc.? Nope. There is no practical value to these things – they don’t even relieve symptoms unless you believe the symptoms will be relieved – and the placebo effect is well documented.

If you’re a “bad” chiropractor, then you will say spinal adjustment will cure all sorts of disease, up to and including cancer. If you’re a “good” chiropractor, then you say that spinal adjustment might help cure back pain or pinched nerves. But if chiropractic were a cure, then you wouldn’t have to go back later this week, or next week. You’d go back the next time you injured yourself. There is no more practical value to a chiropractor than a massage therapist, and the therapist is cheaper.

RELIGION
“God works in mysterious ways.” Well, that kills any predictive value for religion. If there was a predictive value to religion, then the studies on the power of prayer would show conclusively that prayer heals people. Yet the studies, in general, are inconclusive. Only some of the people are cured, and only in cases where the condition is known to sometimes abate in spontaneous remission. Prayer has never been known to cure ALS or Tay-Sachs disease – there’s not a single instance of it. Yet those who believe in the power of prayer are like those who believe a cold reader – they rejoice over the one ”hit” while ignoring the many, many misses. No, I take that back – they don’t ignore them, they attribute them to their “mysterious God”. Still, no practical value.

PHILOSOPHY
There's a lot of talk about free will and materialism but what difference does it make? It seems to me like I'm making decisions all the time. Even not making a decision is making a decision. If I have no free will and yet it seems to me like I'm making decisions, what possible difference is there in my world? If my consciousness exists outside my brain and yet changes to my brain affect my consciousness, then how is that different than if the consciousness resides in the brain? Again, these are things which have no practical value. I cannot act on a deterministic, non-materialist outlook.

CONCLUSION
Many believers tie the unpredictability or miniscule results to quantum mechanics, which anyone with even a rudimentary knowledge will realize has nothing to do with how things work in our physical world. I can totally ignore quantum mechanics and it will make no difference in how I live my life and in how the believer lives his life. Yet that’s the only way they can justify their micro results in a macro world.

[tamiO]

Fabulous post.

Give me a little while so I can mull it over, it's already sparking lots of thought.

[arcticpenguin]

The down side of posting in Banter is that it churns much more quickly than some of the other forums.

[juryjone]

Quote:

Originally posted by arcticpenguin
The down side of posting in Banter is that it churns much more quickly than some of the other forums.

Yeah, I know, but this is so all over the place that I couldn't limit it to one forum. I suppose I could have broken it in two or three, but I figure i'd just be making the same arguments two or three times.

(I'll probably have the opportunity to do that here...)

A very well written post! Bump.

[juryjone]

Shameless bump. I fell no guilt as long as LukeT is starting threads about how many threads there are.

[Jeff Corey]

Quote:

Originally posted by juryjone

I cannot act on a deterministic, non-materialist outlook.

What?

Could you reword that, please?

[Brian]

Yeah. And your non material soul may be forcing you to act in a predetermined way. Or something like that...
Good post, good questions.

----
Even if the results [of influencing RNG's] could be replicated repeatedly, of what significance is this?
----


Um, that the human mind could influence a machine, and that this skill could possibly be cultivated for other things.

And FYI, farmers do participate in society.

[juryjone]

Quote:

Originally posted by Whodini
----
Even if the results [of influencing RNG's] could be replicated repeatedly, of what significance is this?
----


Um, that the human mind could influence a machine, and that this skill could possibly be cultivated for other things.

But these results show no specificity. There is not a specific person being tested who shows that they can force the machine consistently to act in a specific way - forcing it to come up with a specific number. They may be "forcing" it sometimes to come up with a higher number (more 1s than 0s in a binary number) over a large number of trials, but there's really nothing there to cultivate.

Quote:

And FYI, farmers do participate in society.

Of course they do. But it seems that alien abductees are generally people that live in rural surroundings (gotta leave enough room for the spaceship to land without anyone else seeing it).

Let me pt it this way. If a human scientist wants to study apes (who would be even closer to humans than humans are to aliens), the scientist would not pick out an ape that lived off by himself and did not interact with the group except on an occasional basis. No, she'd want to study the apes that were integrated into the society.

Furthermore, she wouldn't worry about the other apes seeing her. Yet aliens are ultra-shy about showing themselves to society at large, yet, for all their advances, they can't seem to keep people asleep during the entire "abduction", and therefore show themselves repeatedly to "abductees".

Quote:

Originally posted by Jeff Corey
What?

Could you reword that, please?

I said, "I cannot act on a deterministic, non-materialist outlook."

Let's see. What I experience day to day is that I have to make thousands of decisions. If I believe that life is pre-determined, how can I act on that belief? Can I stop making those decisions that give me the "illusion" of free will? Or is this "illusion" so complete that nobody can free themselves of this illusion? I say, if this illusion is so total, then there is no way to break out of it, and so it might as well be real. There is nothing I can do to act on a deterministic view of life.

Non-materialism poses the same problem. All of my experiences are seen, heard, felt, tasted, and smelled from within the prison of my head. If my soul exists outside my body, yet the sum total of my experiences, the sum total of me is housed in my brain, then what can I do with the knowledge that I've got something outside my experiences? Can I count that as me? If everything I know is in my brain, and the brain dies, what of me could possibly be in the soul? Should I start downloading my memories into my soul? How does one do that? If there is a transfer, it's all one way - the damaged brain cannot access the soul to get back the memories lost. So what practical value to me is the "knowledge" of a soul?

[lipbone]

Excellent post.

While I agree with your basic tenor, I'm not sure the weight of your argument should be placed on micro results in a macro world.

Basically, quantum physics and other small world environments (think human cells) have been studied, understood, and ultimately manipulated to create macro-world changes.

DNA will (can?) be manipulated to change a person's future by switching off a disease causing gene.

Studying quantum physics has produced rudimentary quantum computing. It's only a matter of time (and studying small things) before we have powerful computers based on this model.

I guess what I'm saying is that the woohoos see the "magic" in science and naturally want to glom off of its potency. It's just a shame that they (the woohoos) don't apply their creative wonder in a more constructive, proven field such as science.

Now that I think about it, I'm not so sure I even agree with your overall message. While it's true that woohoos and woohooistic science don't seem to add any value to the world, I believe it is possible for fantastic, other-worldy ideas and hopes to stimulate real world progress.

Imagine where we would be if noone thought it was possible to calculate mechanically. Or to fly to the moon. Or to fly at all. The motivation for these inventions has to be influenced, in part, by the myths and dreams of eras past. Perhaps the woohoos are dreaming of our future. Who knows?

[juryjone]

Quote:

Originally posted by lipbone
Basically, quantum physics and other small world environments (think human cells) have been studied, understood, and ultimately manipulated to create macro-world changes.

DNA will (can?) be manipulated to change a person's future by switching off a disease causing gene.

Studying quantum physics has produced rudimentary quantum computing. It's only a matter of time (and studying small things) before we have powerful computers based on this model.

...

Now that I think about it, I'm not so sure I even agree with your overall message. While it's true that woohoos and woohooistic science don't seem to add any value to the world, I believe it is possible for fantastic, other-worldy ideas and hopes to stimulate real world progress.

Imagine where we would be if noone thought it was possible to calculate mechanically. Or to fly to the moon. Or to fly at all. The motivation for these inventions has to be influenced, in part, by the myths and dreams of eras past. Perhaps the woohoos are dreaming of our future. Who knows?

Aha, but science brings in reproducability(?). None of these things I discussed is able to be consistently reproduced. Effects of DNA manipulation and quantum computing (in the rudimentary form we've got now) are reproducible. Therefore, they have the ability to affect everyday life, as mechanical calculation and air travel have.

As far as flight being possible, we see evidence of that every day from birds and insects. So of course we know it's possible. And it's not such a big stretch to go from an abacus to being able to mechanically move the "beads". to produce answers. I see your point, but I don't know that you've given the best examples to illustrate it.

Excellant post...unfortunately it is excellant enough that it doesn't cause enough controversy to keep itself bobbing at the top. That always blows.

Only one problem I found that I felt I should comment on:

Quote:

Originally posted by juryjone
If you’re a “bad” chiropractor, then you will say spinal adjustment will cure all sorts of disease, up to and including cancer. If you’re a “good” chiropractor, then you say that spinal adjustment might help cure back pain or pinched nerves. But if chiropractic were a cure, then you wouldn’t have to go back later this week, or next week. You’d go back the next time you injured yourself. There is no more practical value to a chiropractor than a massage therapist, and the therapist is cheaper.

I'm afraid that it does not logically follow; a series of rabies shots, for instance, is what...some 8-12 shots over multiple months? Resetting a bone can take multiple sessions of breaking, setting, coming back weeks later, and doing it all over again, etc.

However, if the treatments last forever, obviously that isn't a cure - it is a treatment.

Also, while not exactly what you said, a good point is to compare the actual effectiveness of chiropracters vs massage therapists, for instance. Anyone know of any studies to that effect, especially as it relates to price?


Good post, though

Juryone,

----
But these results show no specificity. There is not a specific person being tested who shows that they can force the machine consistently to act in a specific way - forcing it to come up with a specific number.
----


But you said originally:


----
Even if the results [of influencing RNG's] could be replicated repeatedly, of what significance is this?
----


So if a person or a group of people could get together and influence a machine with their mind, I'd say that would be very significant.

Then one could remove 1 person from the group, re-do the tests, and see if the results are still there.

This way you could figure out which person or group of people has the skill.

Then one could ask: "Is there anything in common that all of these people have?" (besides the skill)

Then this skill could perhaps be cultivated.

Quote:

Originally posted by juryjone
Shameless bump. I fell no guilt as long as LukeT is starting threads about how many threads there are.

Number 7.

And bump.

edited to add: anyone who ruminates over something for a year and a half before starting a topic on it is aces in my book.

Quote:

Originally posted by juryjone
THE PARANORMAL
Let’s touch on the paranormal first. How about starting with the PEAR experiments that were debated ad nauseam here months ago? They found that, once you whip all the numbers together, there could be a slighter greater result than chance that a random number generator could be influenced in a general direction (i.e., more ones than zeros generated or vice versa). Even if the results could be replicated repeatedly, of what significance is this? Is this of any practical use? “Oh my god, they’ve released a psychic who can make our RNGs slightly less random! Run for the hills!” Yet it seems that this is the best study that there is to offer.

It's irrelevant whether it is of any practical result. The point is it utterly destroys materialism, and given that our mental lives cannot in fact be identified with any physical process, we had better start addressing what the ultimate nature of the self is and whether there is a life after death etc etc.

[Pyrrho]

Quote:

Originally posted by Interesting Ian
It's irrelevant whether it is of any practical result. The point is it utterly destroys materialism, and given that our mental lives cannot in fact be identified with any physical process, we had better start addressing what the ultimate nature of the self is and whether there is a life after death etc etc.

I think there has been a practical result, in terms of sales of related materials. Personally I think it's premature to assume any of these purported effects are genuine, especially the PEAR meta-analysis "effect". Paranormalism has a long way to go before materialism is utterly destroyed, and there's still the problem of those pesky laws of physics.

[juryjone]

Quote:

Originally posted by Whodini
So if a person or a group of people could get together and influence a machine with their mind, I'd say that would be very significant.

Then one could remove 1 person from the group, re-do the tests, and see if the results are still there.

This way you could figure out which person or group of people has the skill.

Then one could ask: "Is there anything in common that all of these people have?" (besides the skill)

Then this skill could perhaps be cultivated.

I must admit I've never read the PEAR tests - I have no background in statistics and therefore the figures are meaningless to me. But the impression I've gotten from reading on them here is that there is no significance until you combine the results. So a single trial may not show any result, regardless of the number of people you have "influencing" the machine. So how do you figure out who "has the skill"?

Suppose someone has been playing the lottery for ten years without winning. This person, one day, gets five out of six numbers correct and receives a significant amount of money. Six months later they win the whole thing. Do you start studying this person to try to figure out how they influenced the lottery? Or do you chalk it up to coincidence? How do you "cultivate" what seems to be a random gift?

Quote:

Originally posted by Interesting Ian
...given that our mental lives cannot in fact be identified with any physical process, we had better start addressing what the ultimate nature of the self is and whether there is a life after death etc etc.

If mental processes can't be identified with physical processes, if there's no tie between the two, then there's no question about life after death. Physical death would not have any impact on mental processes - they would go on.

However, if that's true then occasionally the reverse should prove true - mental processes might stop with no physical causation. I have not heard of this happening, but perhaps you know of a case or two.

[Yahzi]

Moderators should move this to R&P...

I have no comment. Your title says it all.

I will say, this problem of scale seems to be endemic. People don't understand how far away the stars are compared to how far away the planets are. Homeopaths just don't grok the difference between 1.0e-03 and 1.e-30.

Humans divide things into at most 100 parts. Three orders of magnitude is all you need to avoid tigers.

----
I must admit I've never read the PEAR tests - I have no background in statistics and therefore the figures are meaningless to me. But the impression I've gotten from reading on them here is that there is no significance until you combine the results.
----


Juryone,

They did something called a meta-analysis (an analysis of analyses), which is the combining of similar studies where the items of interest were measured in the same, or similar, way.

From this one can get an overall 'effect'.

There is some significance in individual analyses, but when you combine them, you get a very significant overall effect.


----
So a single trial may not show any result, regardless of the number of people you have "influencing" the machine. So how do you figure out who "has the skill"?
----


Some of the single trials do. But, in any case, one would need to do a lot of replication.

If you've got one person who can reliably change the output of a random number generator...does anyone else smell $1 million around here?

But wait...no one has ever succesfully gained that prize...

[Underemployed]

Lazy thinking! Something has an apparently negligible effect so it doesn't matter? Hah!

Paranormal events are a lousy example of this. The law of big numbers allows for statistical flukes. Of course they are bunk.

Why not try the law of unexplained limitations if you want a stick to beat psychics with (eg why can Uri Geller bend cutlery but not crowbars).

Quote:

Originally posted by rwald
If you've got one person who can reliably change the output of a random number generator...does anyone else smell $1 million around here?

But wait...no one has ever succesfully gained that prize...

The issue is one of replication. There hasn't been any reliable replication as far as I know.

And replication is the key to science.

Juryjone,


----
I must admit I've never read the PEAR tests - I have no background in statistics and therefore the figures are meaningless to me.
----


No offense, but if you've never read the articles about PEAR, why do you feel the need to comment on them:


----
How about starting with the PEAR experiments that were debated ad nauseam here months ago? They found that, once you whip all the numbers together, there could be a slighter greater result than chance that a random number generator could be influenced in a general direction (i.e., more ones than zeros generated or vice versa). Even if the results could be replicated repeatedly, of what significance is this? Is this of any practical use? “Oh my god, they’ve released a psychic who can make our RNGs slightly less random! Run for the hills!” Yet it seems that this is the best study that there is to offer.
----


It seems like you are baseing all of your 'knowledge' about PEAR on what was written in this forum. How is that anywhere near being skeptical on the issue of PEAR?

Shouldn't you read some articles on PEAR or something.

There are many of us in this forum who could explain the statistical issues.

[juryjone]

Quote:

Originally posted by Whodini
It seems like you are baseing all of your 'knowledge' about PEAR on what was written in this forum. How is that anywhere near being skeptical on the issue of PEAR?

Shouldn't you read some articles on PEAR or something.

There are many of us in this forum who could explain the statistical issues.

Well, do you think that if I read them that my view on the significance of the results would change? You said yourself, "There is some significance in individual analyses, but when you combine them, you get a very significant overall effect." As a layman in statistical matters, it would seem that if you put together a bunch of results with "some significance", you couldn't possibly get a "very significant" result, just as you can't add up a bunch of test scores of 60 and expect to get a C. I don't know if I'd ever be able to understand a meta-analysis that came up with better results than any single study.

By the way, thanks for getting my name correct. "Juryone"? Even I'm not egotisitcal enough to imagine I'm a jury of one.

Quote:

Originally posted by juryjone


As a layman in statistical matters, it would seem that if you put together a bunch of results with "some significance", you couldn't possibly get a "very significant" result, just as you can't add up a bunch of test scores of 60 and expect to get a C. I don't know if I'd ever be able to understand a meta-analysis that came up with better results than any single study.

The word "meta-analysis" should always raise a red flag. Any research that appeals to meta-analysis for significance has to be scrutinized closely.

A basic problem is something called "the file drawer effect."

Imagine that there are 10 placebo controlled studies looking at the effect of drug X on disease Y. Three of those studies show that 70% of patients getting X improve, compared to 50% getting placebo; the rest are more like 50% vs 50%. Maybe even one study shows that people getting drug X do worse than placebo.

In any of the three studies seeming to show a positive effect for Y, there aren't enough patients to prove that the effect is statistically significant. But when the three studies are pooled, the total number of patients is larger and the effect then becomes statistically significant.

But it's not fair retrospectively picking out only the more positive studies for the pool! The seven studies "left in the file drawer" have to be included somehow.

DrBenway,


I agree with your discussion of the File Drawer Effect. Any competent researcher doing a meta-analysis needs to synthesize the results from all studies with a similar measure, not just the ones with good z-scores.

Juryjone,


----
Well, do you think that if I read them that my view on the significance of the results would change?
----


Well, probably not, but, you are basically just arguing about the article, but you've only read the summary but don't know any of the technical details.

I'm definitely not saying you can't get anything out of it, but rather that you could get more out of it if you read it all.

Bigger is better than the smaller
But bigger and smaller is better than the biggest.
So read the entire article in addition to the abstract.


----
As a layman in statistical matters, it would seem that if you put together a bunch of results with "some significance", you couldn't possibly get a "very significant" result, just as you can't add up a bunch of test scores of 60 and expect to get a C.
----


One certainly can do that. Keep in mind that the opposite could also happen. (if one adds up negative z's and positive z's, they could 'cancel')

A z-score of 1 is not significant at the 5% level, but if you use a meta-analysis summary of (for example)

R = (z1+z2+z3+...+zn)/sqrt(n),
(z's are from a standard normal)

if all the zn's are 1, or larger for example, then you get a very significant result at the 5% level.

Which makes sense because individually they don't mean much, but they are all positive 'effects'.

The thing is, juryjone's original point was that even if the meta-analysis proved that psychics can reliably make a machine output 5% more 1's than it should, so what? If any one person were talented enough to do something more meaningful, then a meta-analysis wouldn't have been needed. It would require a slightly different way of thinking about things, but it would have no practical effect on people's lives.

Rwald,


----
The thing is, juryjone's original point was that even if the meta-analysis proved that psychics can reliably make a machine output 5% more 1's than it should, so what?
----


One couldn't conclude that from a meta-analysis.

But in any case...


----
If any one person were talented enough to do something more meaningful, then a meta-analysis wouldn't have been needed.
----


Understood, but the meta-analysis wouldn't be done with just that one person's results. A meta-analysis would synthesize the results from, say, 100 different people.

[PixyMisa]

Unfortunately, the PEAR reports are worthless garbage. I can't say whether the experiments conducted by PEAR have shown something or not. But I have read the reports, and they are worthless garbage.

Quote:

Originally posted by PixyMisa
Unfortunately, the PEAR reports are worthless garbage. I can't say whether the experiments conducted by PEAR have shown something or not. But I have read the reports, and they are worthless garbage.

LOL.

Care to elaborate on your skeptical treatment of the subject.

[juryjone]

Quote:

Originally posted by Whodini
Keep in mind that the opposite could also happen. (if one adds up negative z's and positive z's, they could 'cancel')

A z-score of 1 is not significant at the 5% level, but if you use a meta-analysis summary of (for example)

R = (z1+z2+z3+...+zn)/sqrt(n),
(z's are from a standard normal)

if all the zn's are 1, or larger for example, then you get a very significant result at the 5% level.

Which makes sense because individually they don't mean much, but they are all positive 'effects'.

Whew. As I told you, it takes very little in the way of statistics for me to get out of my depth. If you haven't "dumbed it down" as much as you could already, could you explain that in layman's terms?

Quote:

Originally posted by rwald
The thing is, juryjone's original point was that even if the meta-analysis proved that psychics can reliably make a machine output 5% more 1's than it should, so what? If any one person were talented enough to do something more meaningful, then a meta-analysis wouldn't have been needed. It would require a slightly different way of thinking about things, but it would have no practical effect on people's lives.

Yes, indeed, that is my original point. Thank you.

I'll try to explain what Whodini's saying. Let's say you have a bunch of experiments, each of which shows a small (but statistically insignificant) correlation. Individually, each experiment doesn't mean anything (it could be due to random chance). But if all those different experiments all had a positive correlation, than maybe there really is a positive correlation. That's the gist of it.

Juryjone,


----
Whew. As I told you, it takes very little in the way of statistics for me to get out of my depth. If you haven't "dumbed it down" as much as you could already, could you explain that in layman's terms?
----


A z-score is something like z = (x-ave of x's)/standard deviation of the x's. It is basically a 'standardized score'. -just a score put on another scale, like Farenheit to Kelvin.

The idea is that while x may have been on a lbs scale, or a height scale, or on a temperature scale, x may have been on another scale in a different analysis, so the scores are standardized so we can compare scores.

Based on the bell curve, a z greater than about 2 (or less than about -2, because the curve is symmetric) is deemed 'significant' at the 5% level.
The z's can take on any value from, say, -10 to 10, where the more positive or more negative the number is, the more 'significant' the result is. Most z's take on values between -3 and 3.

"At a 5% signifigance level' means that if there is no paranormal stuff going on, we'd expect a z this large only 5% of the time or less. So if we get a very very large z, this is evidence against 'no paranormal stuff going on'.

A meta-analysis combines these z's from many experiments. (There are conditions: like they have to be similar experiments where things were measured the same or similar way)

A typical meta-analysis combination of the z's is:

R = squareroot(n)*average of z's,

where n is the number of z's you are combining.

(which is mathematically the same as (z1+z2+z3+...+zn)/sqrt(n), which is what I wrote in the previous message)

We'd be interested in seeing if this R is greater than 2 or less than -2. If it was, the results would be 'significant'.

A z-score of 1 is not significant at the 5% level. But, if all of the z's are mostly of the same sign (+ or -) and are combined, the result is that R could be significant.

Which makes sense because individually they don't mean much, but they are all positive 'effects'.

[PixyMisa]

Quote:

Originally posted by Whodini
LOL.

Care to elaborate on your skeptical treatment of the subject.

I've got you on "ignore", but I expected this sort of response.

Start here.

Someone here posted a further analysis of the PEAR papers addressing some points that I missed. I'm sure you could find it if you ever bothered to look.

[PixyMisa]

Oh yes: PEAR and the Unicorn Hunt

PixyMisa,


You have me on ignore? Uh, ok...


Your 'analysis' amounts to name calling.

The fact that you can't wrap your brain around the abstract is moot.

The fact that a test wasn't blinded doesn't make the science apriori bad.

The fact that the experimenters can dictate the experiment (encourage a playful mood) is not bad. That is what experimenters do, they set the parameters of the experiment.

You said:

----
Not keeping records also being a popular tool of experimental science.
----


But they did NOT say they didn't keep records. They said that they did not "maintain systematic records on the relative effectiveness of the various personal strategies developed by the participants in their approach to the task, or on any of their psychological characteristics."

That is hardly the same thing as saying no records were kept, period.

For example, you completely ignore, in your review, the sentences RIGHT AFTER all of that where they do talk about some of the things they recorded. You also ignore all the tables and graphs they had in the paper. Not to mention all their appendices. You think that these magically appeared without them keeping some type of records?

They also have several sections where their p-values were NOT significant. So so much for the 'only publishing the hits' theory.

Can you explain the fact that the 653-trial formal database had a composite z-score of 5.418 (pvalue < 3x10^ -8 )? And I'll give you a hint, saying "meta-analysis" as your answer doesn't explain anything.

[The Central Scrutinizer]

Quote:

Originally posted by Interesting Ian

...we had better start addressing what the ultimate nature of the self is and whether there is a life after death etc etc.

There is no life after death. That subject has now been addressed.