Beta

Slashdot: News for Nerds

×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Beer-Drinking Scientist Debunks Productivity Correlation

kdawson posted more than 6 years ago | from the sipping-a-magnificent-pacific-northwest-microbrew-porter dept.

Science 130

austinpoet writes in with a blog post debunking the theory we discussed a few days back that scientists' beer consumption is linearly correlated with the quality of their work. Chris Mack, Gentleman Scientist and beer drinker, has analyzed the paper and found it is severely flawed. From his analysis: "The discovered linear relationship between beer consumption and scientific output had a correlation coefficient (R-squared) of only about 0.5 — not very high by my standards, though I suspect many biologists would be happy to get one that high in their work... Thus, the entire study came down to only one conclusion: the five worst ornithologists in the Czech Republic drank a lot of beer."

cancel ×

130 comments

Simply put (5, Funny)

schnikies79 (788746) | more than 6 years ago | (#22841202)

beer > coffee/caffeine

Re:Simply put (5, Funny)

explosivejared (1186049) | more than 6 years ago | (#22841302)

beer > coffee/caffeine >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> girls

Re:Simply put (3, Funny)

Phil246 (803464) | more than 6 years ago | (#22841494)

girls?
what is this mythical substance of which you speak?

Re:Simply put (5, Funny)

edwardpickman (965122) | more than 6 years ago | (#22841832)

Beer=Pretty Girl>Morning=Ugly Girl

Re:Simply put (1)

glavenoid (636808) | more than 5 years ago | (#22842140)

We here at slashdot tend to forgive logical fallacies from time to time, but we, *in general* tend to loath tautologies. Just FYI.

The More You Know...

Re:Simply put (3, Funny)

Dunbal (464142) | more than 5 years ago | (#22842204)

Funny, for me Beer = Pretty Girl = embarrassment = sleeping alone = hangover.

Re:Simply put (0)

Anonymous Coward | more than 5 years ago | (#22842312)

Yeah, beer mixed with caffeine makes one look shifty.

I've found a new co-relation: (1, Funny)

ILongForDarkness (1134931) | more than 5 years ago | (#22843532)

Social activity leads to beer consumption

Social activity leads to "rubbing shoulders" with those with the ability to affect your career. Argo:

Social activity with beer would likely lead to scientist's getting tenure; most people will agree that tenure doesn't help produce "quality" papers (defined as those likely to be sited a lot and in prestigious journals). Just like most nobel prize winners tend to do little productive work in their field after that accomplishment. I'm from a physics background, our nobel prize winners have been known to go into such great research areas as "proving aliens exist" and throwing temper tantrums that quantum mechanics doesn't "feel" right to them.

Not to say that the tenure system is bad, we need independence/security for researchers so they aren't forced too much to do what will get them grants and keep them in a position. As well, I'd rather have the heavy beer drinking crowd safely behind a desk then operating a crane above my office. However, I don't think it is great that the entire university heirachy revolves around getting tenure as a status symbol. No one's job should be so secure that they cease having to try.

Correlation is not causation.... (-1, Troll)

Anonymous Coward | more than 6 years ago | (#22841212)

Not only have we discussed this on /. about a week ago, it's just plain wrong anyway, according to [yahoo.com] .

Hmm... do we need either of these studies? (2, Informative)

PC and Sony Fanboy (1248258) | more than 6 years ago | (#22841232)

C'mon, I thought the (ancedotal) evidence proving(?) that beer is and isn't good for productivity is adequete! It should say that beer, in certain levels, is good for productivity, and in excess ... it is bad. Really, people write papers to prove this?

Re:Hmm... do we need either of these studies? (5, Funny)

Tranzistors (1180307) | more than 6 years ago | (#22841344)

When bored, hackers write viruses, scientists - papers.

Disclaimer, I am non of the above.

Re:Hmm... do we need either of these studies? (3, Insightful)

Anonymous Coward | more than 5 years ago | (#22842292)

Hm, I'd bet you're bored; that's probably why you're on Slashdot.

Re:Hmm... do we need either of these studies? (1)

psychicsword (1036852) | more than 5 years ago | (#22843446)

I go on slashdot or Stumbleupon both prevent any real work from getting done

More research required (1)

The Fun Guy (21791) | more than 5 years ago | (#22843508)

When bored, hackers write viruses, scientists - papers.

You can be sure this is true by the comments posted to the blog, many of which run, "Hey, instead of trashing the Czech paper, you should conduct your own study and publish counter-results."

For the record, IAAS. (and I drink beer)

Re:Hmm... do we need either of these studies? (5, Funny)

ArsonSmith (13997) | more than 6 years ago | (#22841346)

I think what you refer to is known as the "Ballmer Peak" shown on this graph:

Here [xkcd.com]

Re:Hmm... do we need either of these studies? (1)

nbert (785663) | more than 6 years ago | (#22841430)

To add another point against such studies: They don't investigate cause and effect, they simply say that scientists consuming beer will produce worse/better results. Let's assume I love beer (right) but I don't drink any because I fear the consequences of alcohol consumption (wrong). Of course people can argue that my consumption will have an impact on the work I do*. But my opinion about alcohol consumption also says something about my personality - I love to do things which are not in my best interest and I'm quite confident that it influences my approach to work-problems regardless of beer consumption. So if I turn into a beer loving but non-drinking scientist I might cause the same results statistically.

In my opinion this study says as much as the "Cat owners are less likely to get cancer" study - a fun-fact, but it's not the cat's impact on my body reducing the risk. I won't reduce the probability of getting cancer by buying a cat...

*Within limits of course. Won't argue that it will make a difference if I drink excessively.

Re:Hmm... do we need either of these studies? (4, Funny)

cayenne8 (626475) | more than 6 years ago | (#22841600)

Well, I don't care if some people DO think beer is bad for ya....

I refuse to give up one entire food group!!!

Re:Hmm... do we need either of these studies? (1)

nbert (785663) | more than 6 years ago | (#22841690)

Then I have good news for you: Over here people say: "3 beers is like one steak". My only concern is that I feel kind of different after 3 beers at lunch. Coming to think of it I never had 3 before the evening - even one makes me sleepy during daytime...

Not only that (4, Interesting)

lakeland (218447) | more than 6 years ago | (#22841438)

They've looked for a linear correlation, so if what you've said is true then the analysis they used wouldn't find it.

In order to find a correlation where the input IV (beer consumption) has an optimal value, you would have to do the regression on a transformation of the variable. Perhaps a quadratic would suffice, or else abs(X - k) for some unknown value of k.

Re:Not only that (3, Informative)

hao3 (1182447) | more than 5 years ago | (#22841942)

couldn't you just take a differential of the linear regression and optimise that?

Re:Not only that (1)

darkfish32 (909153) | more than 5 years ago | (#22841982)

How can you optimize a constant? This is news

Re:Not only that (1)

lakeland (218447) | more than 5 years ago | (#22843112)

Interesting idea, they're very different branches of mathematics so I'm having trouble working out how to combine them.

The idea in regression is to transform the IVs such that there is a linear relationship between them and the DVs. The transformations people make of IVs to make the relationship simple are a bit of a black art. Most people just get by with log since it solves any polynomial. It's easy enough to just keeping adding higher order polynomials until regression predicts a coefficient of 0 to tell you that you've gone too far, but that doesn't help much if the equation you're trying to predict parameters for is not efficiently modelled by a polynomial.

As for using differentiation to find the optimal transformation function, it's an interesting idea and I'm too tired now to work out if you could use it. A google search doesn't turn up anything quickly, with the following at least trying to determine the transformations automatically instead of guessing. http://pubs.acs.org/cgi-bin/abstract.cgi/ancham/1991/63/i20/f-pdf/f_ac00020a022.pdf?sessid=6006l3 [acs.org]

The problem I keep coming back to is predicting the height of a ball bobbing on the surface of the sea given all the appropriate parameters. The see is best modelled as the combination of waves (duh), but I can't think of anything except the intuition of the modeller that would detect this case and suggest log was not an appropriate general function. I recall covering hmm, was it Maclaurin expansion, in my senior numerical methods course, but I never thought of applying that to regression at the time. Relying on google again turns up http://www.springerlink.com/content/44teyxefx9pa8058/ [springerlink.com] which looks relevant but I'm not subscribed to springer so can't view any more than the abstract.

Re:Not only that (2, Funny)

l0cust (992700) | more than 5 years ago | (#22843770)

I am pretty sure we will need one full crate of lager before most of us can make out wtf you two guys are talking about.

Re:Not only that (5, Funny)

irc.goatse.cx troll (593289) | more than 5 years ago | (#22842052)

In order to find a correlation where the input IV (beer consumption)


If you consume beer through an IV I think you're a different type of drinker.

Re:Not only that (1)

popmaker (570147) | more than 5 years ago | (#22843784)

You mean the kind of drinker that has taken the "beer-bong-on-helmet" a little too far?

Re:Not only that (0)

Anonymous Coward | more than 5 years ago | (#22843718)

Or if they still wanted to use standard linear regression (scientists don't consider statistics to be worth learning or doing correctly for some reason...) they can take a survey with questions of the form "How often do you consume moderate amounts (1-2 glasses) of alcohol?" instead of "How many glasses do you drink when you drink alcohol?" This may even be a better way to ask the questions; you can ask for "moderate" and "extreme" and look for positive and negative correlation respectively - there may be some controlling-variable issues; too early in the morning and I had too much whisky...

Re:Hmm... do we need either of these studies? (1)

AB3A (192265) | more than 5 years ago | (#22843470)

Yes, they do. [wikipedia.org]

A bored scientist is no better than any other bored professional. You don't want to see what happens next...

earth to Cap'n Obvious... (2, Insightful)

Anonymous Coward | more than 6 years ago | (#22841234)

I think it's safe to say that the paper they are "debunking" was meant as a joke.

Re:earth to Cap'n Obvious... (4, Insightful)

Dolohov (114209) | more than 6 years ago | (#22841298)

Who's to say the "debunker" isn't just having fun himself?

Re:earth to Cap'n Obvious... (1)

CopaceticOpus (965603) | more than 5 years ago | (#22842640)

The debunkers should try getting drunk and reviewing the paper again. See if they get the same results.

In Other news (5, Funny)

omarmarosh (1261102) | more than 6 years ago | (#22841246)

Scientists Claim there is a direct correlation b/w pot smokers and an amazing talent to link string theory with life on mars

Re:In Other news (5, Funny)

dreamchaser (49529) | more than 6 years ago | (#22841376)

Scientists Claim there is a direct correlation b/w pot smokers and an amazing talent to link string theory with life on mars


That was based on a misquote. The original conversation was 'Dude...do you think they have string cheese on Mars...like that would be so coool. Pass the Doritos?'

Maybe (2, Funny)

iminplaya (723125) | more than 6 years ago | (#22841258)

It's more about the quality of their beer. Not that I have anything against Pilsen. I think they make a perfectly fine beer over there.

!news (-1, Troll)

psychodelicacy (1170611) | more than 6 years ago | (#22841278)

I know it's a holiday and therefore news is slow. But really. When we discussed this a few days ago it wasn't news. It isn't news now. Maybe it would fit on Idle.

Re:!news (1, Funny)

Anonymous Coward | more than 6 years ago | (#22841858)

It's a kdawson post. It's to be expected.

Re:!news (0, Offtopic)

psychodelicacy (1170611) | more than 5 years ago | (#22842130)

Seems I'm a Troll, and Insightful, and Overrated. I always knew I had identity issues, but this is one to tell my therapist ;)

Question: there seems to be a lot of complaining recently about specific people posting stories that aren't seen as well-researched or newsworthy. Why does this happen? I assumed that editors just evaluated stories as they came in against objective criteria - is that naive? Sorry if this is offtopic.

Re:!news (3, Insightful)

SL Baur (19540) | more than 5 years ago | (#22842510)

It beats the daily Microsoft Windows Vista article(s). Those don't get interesting no matter how many beers you drink before reading them.

Performance enhancing drugs (4, Interesting)

blackC0pter (1013737) | more than 6 years ago | (#22841352)

So beer may or may not hinder a scientist's creative abilities. On the flip side, will scientists ever start taking drugs in order to improve their skills? Would this ever lead to drug testing researchers that announce amazing new scientific breakthroughs? (sort of far fetched but an interesting idea nonetheless).

Re:Performance enhancing drugs (3, Insightful)

ScrewMaster (602015) | more than 6 years ago | (#22841400)

Would this ever lead to drug testing researchers that announce amazing new scientific breakthroughs? (sort of far fetched but an interesting idea nonetheless).

Sure it would. I can see it now:

"I just got the results of your drug test ... apparently you've not been taking your drugs. They're a job requirement you know. I understand that the enhancer pills give you migraines, but we promised BigMegaCorp that breakthrough they've been wanting, and you do like your job, don't you?"

Re:Performance enhancing drugs (1)

Planesdragon (210349) | more than 6 years ago | (#22841744)

On the flip side, will scientists ever start taking drugs in order to improve their skills?
They've been doing it since the dawn of human civilization. Coffee, Cigarettes, and Alcohol are all imbibed by white-collar workers chiefly for the effect they have on the psyche.

Re:Performance enhancing drugs (1)

SL Baur (19540) | more than 5 years ago | (#22842538)

Coffee, Cigarettes, and Alcohol are all imbibed by white-collar workers chiefly for the effect they have on the psyche.
Heh. Coffee and cigarettes is the Breakfast of Champions. Beer is for the soul. Or something like that, I think. Oh dang it! I just spilled my beer. Hold onto this while I wipe up my keybbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb

Re:Performance enhancing drugs (1)

ZeroExistenZ (721849) | more than 6 years ago | (#22841762)

I've read before that a nobel price winner formulated his theory utilizing psychedelics.

Would this ever lead to drug testing researchers that announce amazing new scientific breakthroughs
No.

Science is not a "competition", thus using "performance enhancing products" cannot invalidate the result. The result in science is approximation of truth and understanding. If it helps being high to formulate a certain theory, formulate it and eventually create the foundations for others to build further on, it isn't something that should be "invalidated" because of the means of aqcuiring that knowledge.

Re:Performance enhancing drugs (4, Informative)

hitchhacker (122525) | more than 5 years ago | (#22842174)

I've read before that a nobel price winner formulated his theory utilizing psychedelics.
I believe you are referring to Kary Mullis [wikipedia.org] . He wrote a book about it titled "Dancing Naked in the Mind Field" [amazon.com] :

Kary Mullis won the Nobel Prize for his invention of the polymerase chain reaction, a chemical procedure that allows scientists to "see" the structures of the molecules of genes. Mullis is no shy, socially inept bench chemist, though; on the contrary, he has led as big and full a life as possible, opening himself to experiences like hallucinogenic drugs, surfing, casually handling dangerous chemicals, and taking shots at the sacred cows of science.

Also, the famous mathematician Paul Erdos [wikipedia.org] used amphetamines for this purpose:

His colleague Alfréd Rényi said, "a mathematician is a machine for turning coffee into theorems", and Erdos drank copious quantities. (This quotation is often attributed incorrectly to Erdos.) After 1971 he also took amphetamines, despite the concern of his friends, one of whom (Ron Graham) bet him $500 that he could not stop taking the drug for a month. Erdos won the bet, but complained during his abstinence that mathematics had been set back by a month: "Before, when I looked at a piece of blank paper my mind was filled with ideas. Now all I see is a blank piece of paper." After he won the bet, he promptly resumed his amphetamine habit.

-metric

Re:Performance enhancing drugs (1)

glwtta (532858) | more than 6 years ago | (#22841874)

Would this ever lead to drug testing researchers that announce amazing new scientific breakthroughs?

To what end, exactly? If it's positive, everyone just agrees to forget the results of their research?

Re:Performance enhancing drugs (0)

blackC0pter (1013737) | more than 5 years ago | (#22841956)

To what end, exactly? If it's positive, everyone just agrees to forget the results of their research?

This is exactly the major ethical dilemma that society would face when dealing with drug-enhanced discoveries. Any new science that improves society should be accepted in order to improve the world. But how do you accept these discoveries without supporting (albeit indirectly) the illicit drugs that aided in the formation of this new science? Does the end always justify the means?

To be honest, I don't have an answer to these questions.

Re:Performance enhancing drugs (1)

insertwackynamehere (891357) | more than 5 years ago | (#22842082)

I do: If someone can find the cure for cancer but for some reason they need to drop acid in order to do so, then they should. Of course I am not saying I forsee this happening ever but if it came down to that, then hell yeah, trip your balls off.

Re:Performance enhancing drugs (1)

Provocateur (133110) | more than 5 years ago | (#22842964)

Even worse: if they already found the cure, and this certain scientist is still dropping acid, months after the cure had been found, would *you* have the heart to tell him, It's over, man. Give up the dope?

Heretical alchemy (1)

TapeCutter (624760) | more than 5 years ago | (#22842598)

The only "ethical dilemma" is wether or not we should allow the government to dictate what substances adults can and cannot put into their bodies.

"how do you accept these discoveries without supporting...[XYZ]?"

Does acceptance of Newton's Principa Mathematica automatically infer I support teaching math via 'visions' from a bowl of mecury?
Should I have read and supported the roughly one million words Newton wrote on the number 666 before I look at pictures from the Hubble telescope.
Must I support people sticking pins into their own eyes before I accept Newton's theory of light?

Scientists suffer from human frailty just like the rest of us, by all accounts Newton was both an obnoxious prick and one of the most prolific and profound polymaths that ever lived. What a tradgedy it would have been had he been burnt at the stake for his heretical alchemy.

Re:Performance enhancing drugs (1)

insertwackynamehere (891357) | more than 5 years ago | (#22842066)

talk to every engineer in the 70s who made modern computing what it is today

Re:Performance enhancing drugs (1)

pimpimpim (811140) | more than 5 years ago | (#22843260)

As a scientist, I have wondered myself why this doesn't seem to happen very often, and I think I found an explanation: the salary of a scientist is mostly not sufficient to ensure a frequent intake of stimulating drugs. Nor for a visit to a good detox/rehab clinic.

Try bankers instead. I live close to Switzerland and it has quite the name of being a drugs paradise. I would also like to know what the people where taking that thought trading "subprimes" was a good idea, that certainly wasn't beer but must have been some very strong hallucinogenic stuff.

A lot of scientists might actually act like they're on drugs, but that is just because they are crazy!

Sketch... (5, Funny)

amccaf1 (813772) | more than 6 years ago | (#22841362)

[...] the five worst ornithologists in the Czech Republic drank a lot of beer [...]


This has to be a lost Monty Python sketch, right?

Re:Sketch... (5, Funny)

darkfish32 (909153) | more than 5 years ago | (#22841992)

I'm pretty sure, knowing the Czechs, that the five best drank their fair amount as well.

Mod Insightful (0)

Anonymous Coward | more than 5 years ago | (#22842714)

I just used my last mod point, or I would have gladly modded this up.

Give Debunk a rest (0)

Anonymous Coward | more than 6 years ago | (#22841390)

I agree this is probably all in fun (ha ha), but can we give the "debunking" claims a rest? Nowadays, it seems everybody and his brother is an "armchair gentleman scientist and beer drinker", and in an afternoon, a few hrs of drinking, come up with their own hypothesis. I guess in these days of the internet age we can give up with the foolishness of peer review and the like? But please, do not call this "debunking", it's more like "drunken munchies" if anything



Besides, seriously, there has been some interesting studies that creative folks, especially writers, musicians, do their best work on the wagon. Fitzgerald, Hemingway, famous drunks. Consider all the great musicians dead of drug overdoses. Correlate that, kids.

Re:Give Debunk a rest (1)

budword (680846) | more than 6 years ago | (#22841638)

Hem wrote in the morning, standing up. Sober. Yeah he drank, but he wrote sober. David

We all know what to do now: (5, Insightful)

Anonymous Coward | more than 6 years ago | (#22841396)

More research is needed.

Re:We all know what to do now: (4, Funny)

oldhack (1037484) | more than 6 years ago | (#22841538)

Some suggestions:

Pilsener Urquell vs. Milwaukee's Best
Budvar vs. Old Milwaukee

Re:We all know what to do now: (1)

gardyloo (512791) | more than 6 years ago | (#22841750)

I think the point is to show a correlation (or not) between intake and quality of work. It's not to make people sick!

Re:We all know what to do now: (2, Funny)

Maljin Jolt (746064) | more than 5 years ago | (#22842454)

Pilsener Urquell vs. Milwaukee's Best
Budvar vs. Old Milwaukee

Type Error: can't compare incompatible types.

Re:We all know what to do now: (1)

houghi (78078) | more than 5 years ago | (#22843380)

So basicaly beer vs. Non beer.

You could use the American Beers for the double blind tests.

Hiccup! (1)

matchewg (669643) | more than 5 years ago | (#22842516)

Whtao said evver beeeaara beeeeeeeeeeee bbaad for youya ?

Few... (3, Funny)

Josh Booth (588074) | more than 6 years ago | (#22841426)

So it's safe to drink beer again. And to think I was actually going to cut down!

Re:Few... (1)

SlashWombat (1227578) | more than 6 years ago | (#22841514)

'X' = an unknown quantity ... and we all know what 'P' is. (Relates to drinking lots of beer!)

Of course, I should point out that "slash" in Australia is slang for 'P', so what does slashdot mean in that context?

Re:Few... (1)

Dunbal (464142) | more than 5 years ago | (#22842186)

Actually "P" comes from ethanol's ability to inhibit ADH.

      Sorry, just a biologist's perspective.

Re:Few... (1)

kramulous (977841) | more than 5 years ago | (#22843158)

The dot is the cork bobbing in the toilet because, being a drunk bastard, have yet to learn aim.

Some alcohol is good ... to a point (1, Informative)

Anonymous Coward | more than 6 years ago | (#22841432)

http://aje.oxfordjournals.org/cgi/content/abstract/161/3/228 [oxfordjournals.org] "... moderate levels of alcohol intake may be associated with improved cognitive function and reduced risk of cognitive decline and dementia."

Social drinking leads to better job performance and career success. http://www.ithaca.edu/ithacan/articles/0610/05/opinion/2drinking_.htm [ithaca.edu]

Excess alcohol consumption, on the other hand, is almost always a bad thing. There are some studies that show the benefit of moderate consumption but there is no studies that show that heavy consumption is anything but bad.

xkcd was there first (2, Informative)

Midnight Warrior (32619) | more than 6 years ago | (#22841448)

The comic xkcd was there first and called this effect the Ballmer Peak [xkcd.com] . Most likely, this effect was also tried in Vista and Vista SP1 design meetings, but the balance was all wrong and didn't come out as (they) expected.

Re:xkcd was there first (1)

Rampantbaboon (946107) | more than 6 years ago | (#22841588)

Microsoft used all their money to buy some fine blow, unfortunately the effect is mitigated with cocaine.

Re:xkcd was there first (5, Informative)

Anonymous Coward | more than 6 years ago | (#22841662)

The comic xkcd was there first and called this effect the Ballmer Peak.

"Ballmer peak" is, FYI, a joke [wikipedia.org] that's going over the heads of all you science-illiterate server monkeys.

Re:xkcd was there first (2, Interesting)

MrMunkey (1039894) | more than 5 years ago | (#22842182)

I used to work with someone who was on the team that worked on Visual Fox Pro back in the early days. She said that the company did provide alcohol from time to time (I think it was Fridays, but I could be remembering wrong). I'm not saying that xkcd wasn't a joke, I just wanted to point out that there might be a grain of truth to it.

Re:xkcd was there first (0)

Anonymous Coward | more than 5 years ago | (#22843338)

4: informative on the parent???!! Are the mods all pissed?

Wouldn't surprise me (2)

sam_handelman (519767) | more than 6 years ago | (#22841462)

I know scientists who devote their entire lives to their work, never go out, never have a good time, have no children (or never see them), etc. etc.

  Are they *better* scientists? I don't think so.

  Are they *more productive* scientists? Not in every case, but on average, yeah, I'd say they are. There are situations where spending all your time on work and neglecting other aspects of your life is a self-defeating proposition, especially in creative work (which generally includes science, although what scientists actually *do* varies a lot from one scientist to another.)

  But burn-out aside, if you're willing to sacrifice other aspects of your life, you can get more science done. Pretending that this is not, generally speaking, true, because you want to pretend that it doesn't cost you anything to have a life, is not productive.

  That said, the article-author is right about the statistics. Bad Czechs!

Re:Wouldn't surprise me (0)

Anonymous Coward | more than 6 years ago | (#22841598)

man, If I was living in Czech Republic and were on that situation you described: couldn't get a date, didn't go out, had no sex, etc. I would probably resort to beer so I could forget my pain. Czech girls are damn hot! They are some sort of Europe's Brazil over there...
So I won't hold those poor ornithologists guilty. Think about that: you are outside observing some birds, and then you just see some hot mommas sunbathing naked? And you stand no chance to try a reproductive act with them? God, better get some really cold beer to drown myself into...

in the social sciences... (0, Troll)

tronbradia (961235) | more than 6 years ago | (#22841464)

In social science .5 is huuge! they don't even usually square r-scores in social science because it's so depressing. .5 is a MASSIVE correlation in social science. Consider how many factors are involved in research success: luck, competence, etc. So if these findings actually show causation (which, admittedly,l they might not), that would mean that beer results in 50% of success or failure, and all the luck and technical skill and social factors that go into success combined can only match beer, with another 50% of the variance. I would go so far as to say that such a high correlation actually makes causation almost impossible; there must be a lot of poor scientists drowning their sorrows and whatnot that this is also taking into account.

Re:in the social sciences... (2, Insightful)

Bryan Gividen (739949) | more than 5 years ago | (#22842042)

Quote: "In social science .5 is huuge!" Reply: I respectfully disagree. r^2 = .5 is a good correlation, but it is not huge, even in the social sciences. Not to mention that in a study such as this one, there are some serious lurking variables which are most likely not accounted for. If you were to control beer drinking with another variable (say, time spent in the office or some other better variable), I would dare say the t-stat would be entirely insignificant. Quote: "so if these findings actually show causation (which, admittedly,I they might not)"... Reply: They definitely do not show causation. This is an observational study, not an experiment. No observational study can show causation, only correlation. To determine causation, experiments using factorial design and variable controlling techniques are a must.

That Explains... (3, Interesting)

Black-Man (198831) | more than 6 years ago | (#22841484)

I had a friend who always cracked open a cold one when he sat down to work (while at home, of course). I could never understand it - but he worked like a maniac. And he did it for years... until he failed a drug test and was fired. He was a manager for a large pharmaceutical manufacturer. Go figure...

Perhaps there is a cause and effect (4, Funny)

Peter Cooper (660482) | more than 6 years ago | (#22841618)

If you were one of the five worst scientists in a field in the Czech Republic, you'd probably turn to drink, right?

Talk about wrong profession! (1, Funny)

Anonymous Coward | more than 5 years ago | (#22842390)

Our next speaker is Dr. Ivan Crow, well known as one of the five worst ornithologists in the Czech Republic, author of Using Airguns Correctly and The Prague Beer Guide. He will be talking to us about "Birds and why they suck".

Re:Perhaps there is a cause and effect (1)

aralin (107264) | more than 5 years ago | (#22842480)

Contributing to it could be that Czech Republic has the highest beer consumption per capita of all countries in the world.

not just beer (2, Insightful)

FudRucker (866063) | more than 6 years ago | (#22841644)

it depends on the kind of drinker you are, do you drink moderately and only open that first alcoholic beverage later in the evening (after supper)? you know anybody that pops the top off any alcoholic beverage too early in the day and drinks excessively until they are slobbering & stumbling recklessly wont be a good anything (especially a scientist)...

i drink a mixed drink every evening after supper daily and only one, using a shotglass to measure the amount, i do enjoy a mild buzz but i hate being drunk and i dislike drunks since they can cause lots of problems (loss of careers/jobs, wrecked marriages, even cause fatal traffic accidents on the road)...

moderation is the key...

Re:not just beer (0)

Anonymous Coward | more than 5 years ago | (#22842446)

All things in moderation....including moderation.

Re:not just beer (1)

jotok (728554) | more than 5 years ago | (#22843644)

I drink at work.

My boss buys us racks of beer and anytime after 3 in the afternoon if you enter our office you will see us with beers out, brainstorming, etc. You will also be offered a beer.

We get some of our best work done this way.

So, how did the 5 ornithologists respond to him? (4, Funny)

GodfatherofSoul (174979) | more than 6 years ago | (#22841674)

They gave him the bird!

Is this really that surprising? (1)

digitalderbs (718388) | more than 6 years ago | (#22841698)

Seems to me that the authors of this study were heavy beer drinkers.

Pipe smoking increases scientific productivity? (1)

bkaul01 (619795) | more than 6 years ago | (#22841700)

If we're going with anecdotal evidence here, Einstein was a renowned pipe smoker, so ... smoking must be the new wonder-drug for intellectuals. Maybe soon we'll see nicotene tests on college campuses just like we see steroid tests in MLB.

"Gentleman Scientist" is confused.... (4, Interesting)

Ardeaem (625311) | more than 6 years ago | (#22841776)

The "debunker" has confused two related statistical concepts: correlation, measured by r, and proportion of variance accounted for, measured by R^2. if the R^2 is truly .5, that would be fantastically high; it would mean that 50% of the variance in the "quality of work" measure is explained by beer drinking. Think about that for a minute. To determine how low or high an R^2 measure is, you have to look at what is being modeled, in this case R^2=.5 is very high.

If, on the other hand, he means the correlation coefficient r=.5, that means that R^2=.25. Still, a quarter of the variance in "work quality" is explained by beer drinking. That is still very high.

His point about outlying ornithologists and the points not being independent may still be valid; determining if they are is an empirical matter. Do these outlying scientists, in fact, socialize together? What other sources of nonindependence might there be, and do they affect THIS data set? Also should we really claim that 5 out of 34 (15% of the sample!) constitute OUTLIERS? Those aren't outliers, those are a subpopulation.

He didn't debunk the study; he rather raised some interesting questions.

Re:"Gentleman Scientist" is confused.... (1)

hyades1 (1149581) | more than 6 years ago | (#22841824)

There are times when real science transcends mere mathematics. So kindly quit making sense, shut up, and drink this (if I were nearby, a beer would be in your immediate future).

Cheers!

Re:"Gentleman Scientist" is confused.... (1)

dookiesan (600840) | more than 5 years ago | (#22842238)

Who cares about a covariance estimate? Maybe all of the variance is in those 5 samples. Cross validate and see how well you can predict academic performance with and without beer drinking as a predictor.

Re:"Gentleman Scientist" is confused.... (1)

Nutty_Irishman (729030) | more than 5 years ago | (#22842298)

Also should we really claim that 5 out of 34 (15% of the sample!) constitute OUTLIERS? Those aren't outliers, those are a subpopulation.
Removing those 5 points drops the correlation down to -0.35. The pearson correlation assumes that both data points are normally distributed-- the citation data are, the drinking data are not. Both the 5 heavy drinkers and the 4 light drinkers move the data away from a normal distribution, which makes any interpretation of pearson correlation rather sketchy. With that said, even the ranked order tests perform moderately well (-0.42 for kendals, -0.57 for spearman).

Here are the stripped data from the image in the paper (it's in image coordinates, not the original coordinates)
y = c(-200,-165,-250,-226,-305,-230,-250,-233,-265,-155,-245,-269, -296,-136,-250,-250,-214,-165,-283,-250,-250,-200,-298,-302,-367,-294,-412,-214, -305,-307,-352,-268,-358,-352);
x = c(111,114,127,140,161,177,186,202,202,207,225,225,225,242,242,248, 276,286,292,301,311,313,313,325, 325,334,334,338,350,355,362,367,398,427);

Re:"Gentleman Scientist" is confused.... (2, Insightful)

glwtta (532858) | more than 5 years ago | (#22842804)

Wait a minute, this "study" was done on 34 people? And the method for choosing them was "that guy's buddies"?

And we are actually spending time talking about it?

Re:"Gentleman Scientist" is confused.... (1)

jamesh (87723) | more than 5 years ago | (#22843660)

The "debunker" has confused two related statistical concepts

I wouldn't pay him any attention anyway, he's a self confessed beer drinker and so by definition doesn't know what he's talking about.

R^2 = 0.5 Ain't Bad (4, Informative)

DynaSoar (714234) | more than 6 years ago | (#22841806)

R-squared is the amount of variance accounted for by the variable in question. That means half their productivity is explained by beer drinking, and half on all other variables combined.

As a comparison, 0.3 is pretty much the top end R-squared in personality psychology. that field is built on correlations that account for no more than 10% of the observed variance.

To combine the two, it's far more likely that TFA didn't actually measure beer drinking, but rather how much beer those scientists who drank beer would admit to drinking. Those who'll drink it are probably more likely to relax, which will make them more productive, and those who will admit it are less likely to fall prey to negative opinions of others, a major source of which is reviewers' comments on papers submitted for publication. Such comments are often undeservedly harsh, and in many cases coming from someone who doesn't know as much as the author about the topic. That can turn away those who place great store in the opinions of others, especially perceived authorities.

Next, on to Russia and WOTKA!

Re:R^2 = 0.5 Ain't Bad (1)

WhoBeDaPlaya (984958) | more than 5 years ago | (#22841974)

I'd like their prefer some t/F ratio effects test (together with alpha and beta).

Re:R^2 = 0.5 Ain't Bad (3, Insightful)

symes (835608) | more than 5 years ago | (#22843198)

Indeed - but with such a small sample size the researchers would not have been able to adjust for exposure, or age in this case. My guess is that beer consumption declines with age and science is generally cumulative (the longer you do science the more papers you produce and therefore the higher the probability of writing something of interest). In other words, age could easily explain this beer/science relationship - younger scientists drink more - as could a whole host of other variables.

Re:R^2 = 0.5 Ain't Bad (2, Informative)

cvd6262 (180823) | more than 5 years ago | (#22843372)

That means half their productivity is explained by beer drinking, and half on all other variables combined.

I agree with the first part, but not with the second. R^2 of .5 is quite good in social/behavioral sciences*, but it does not mean that "all other variables" only account for half the variance in performance because other variables could "share" the variance associated with beer drinking.

For example, sociability might be highly correlated with beer drinking and performance. There is likely to be a lot of "shared variance" between the two predictors, but it is possible that sociability alone would account for more variance in performance than beer drinking. An ANOVA (or equivalent) analysis would partition the variance between the variables and the variable-by-variable interactions.

* In the (US) financial markets, an important stat is how well a particular mutual fund correlates with the S&P 500. R^2 of less than .95 is considered unacceptable (if you're looking for one that tracks).

Whew! (1)

Curunir_wolf (588405) | more than 6 years ago | (#22841810)

Excellent article. My faith in the scientific community is restored.

I can't believe no one said it? (2, Funny)

KGIII (973947) | more than 5 years ago | (#22841964)

*burp*

Doesn't it make sense (1)

Derosian (943622) | more than 5 years ago | (#22842202)

That the 5 worst scientist drink a lot, I would drink a lot too if I was that kind of failure.

His drinking while debunking debunks his analysis! (1)

itsybitsy (149808) | more than 5 years ago | (#22842646)

It's a recursive debunking. Debunking the paper that beer improves productivity while drinking beer itself debunks his own debunking thus nullifying his analysis. This of course leaves us with a quandary that can only be solved by drinking more beer.

Load More Comments
Slashdot Account

Need an Account?

Forgot your password?

Don't worry, we never post anything without your permission.

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>
Create a Slashdot Account

Loading...