Please login or register. Welcome to the Studio, guest!


Quick Links:


newBookmarkLockedFalling

Josh

Josh Avatar
Where were you when Reach fell?

******
Legendary Studio Member

4,806


May 2008
I was flipping through channels yesterday and on my city's public broadcast channel, there was a lady doing an investigative report on incest and sexual abuse within families. I watched for about 3 seconds when I saw an alarming pie chart come up accompanied by her saying that "99% of all incest cases occur within the family." the pie chart was entirely blue with a small orange slice saying "1% other"

So, I hereby dedicate this thread to the stupid people we see every day.

Scorpian

Scorpian Avatar

******
[ Bracket Admin ]

2,457


April 2006
My mom once told me about somebody who got pulled over in our subdivision for running a stop sign. Her excuse? She thought that stop signs only applied to people who don't live in the subdivision.
wat

Lucifer

Lucifer Avatar

*******
Mythical Studio Member

Eunuch
5,665


August 2005
What's the other 1%?

Eric

Eric Avatar



1,442


November 2005
Wow, amazingly brilliant deduction. I really do wonder what the other 1% could possibly be in their minds.

Scorpian

Scorpian Avatar

******
[ Bracket Admin ]

2,457


April 2006
You know, statistics have shown that 89.2% of all statistics are made-up on the spot.
wat

Josh

Josh Avatar
Where were you when Reach fell?

******
Legendary Studio Member

4,806


May 2008
Scorpian Avatar
You know, statistics have shown that 89.2% of all statistics are made-up on the spot.



Including that one?

Chris

Chris Avatar

******
Head Coder

19,519


June 2005
Josh Avatar
Scorpian Avatar
You know, statistics have shown that 89.2% of all statistics are made-up on the spot.



Including that one?


Only if he said 89.3%.

I mentioned this to Josh on MSN, but this reminds me of something we did in class. :P In a matter of about 30 seconds we debunked "one of the most scientific reports ever" by the U of Chicago with pure logic. I won't go into details, because it'd take too long.

Eric

Eric Avatar



1,442


November 2005
Chris Avatar
Josh Avatar



Including that one?


Only if he said 89.3%.

I mentioned this to Josh on MSN, but this reminds me of something we did in class. :P In a matter of about 30 seconds we debunked "one of the most scientific reports ever" by the U of Chicago with pure logic. I won't go into details, because it'd take too long.
You did it in 30 seconds, how long could it take?

Also, are you talking about the june baby anorexia thing or something?

Lucifer

Lucifer Avatar

*******
Mythical Studio Member

Eunuch
5,665


August 2005
I'm definitely curious.

Esplain, Chris.

Josh

Josh Avatar
Where were you when Reach fell?

******
Legendary Studio Member

4,806


May 2008
Eric Avatar
Chris Avatar


Only if he said 89.3%.

I mentioned this to Josh on MSN, but this reminds me of something we did in class. :P In a matter of about 30 seconds we debunked "one of the most scientific reports ever" by the U of Chicago with pure logic. I won't go into details, because it'd take too long.
You did it in 30 seconds, how long could it take?

Also, are you talking about the june baby anorexia thing or something?


They disproved something on the study of who has more opposite sex partners: men or women. They debunked it using really simple logic, too. Only problem is that their logic doesn't take into account a man or woman being faithful while the significant other is cheating. Unless I am mistaken, that should skew it one way or the other.

Chris

Chris Avatar

******
Head Coder

19,519


June 2005
courses.csail.mit.edu/6.042/fall10/mcs-ftl.pdf

5.2.1. We debug it in the course notes as well there. :P Read if you're really that curious.

Josh: Wrong. That man must sleep with another woman, thus that woman also adds to the woman count while the men add too. It's actually really basic graph theory. *shrugs*



Edit: Similar issue summed up very well:

The same underlying issue has led to serious misinterpretations of other survey
data. For example, a few years ago, the Boston Globe ran a story on a survey of
the study habits of students on Boston area campuses. Their survey showed that on
average, minority students tended to study with non-minority students more than
the other way around. They went on at great length to explain why this “remarkable
phenomenon” might be true. But it’s not remarkable at all—using our graph theory
formulation, we can see that all it says is that there are fewer minority students than
non-minority students, which is, of course what “minority” means.


(Quoted from that book above.)


Edit 2: BTW, my bad on attributing "most scientific study ever" to the wrong source. It was ABC News not U of chicago.


Last Edit: Oct 27, 2010 20:44:21 GMT by Chris

Josh

Josh Avatar
Where were you when Reach fell?

******
Legendary Studio Member

4,806


May 2008
Chris Avatar
courses.csail.mit.edu/6.042/fall10/mcs-ftl.pdf

5.2.1. We debug it in the course notes as well there. :P Read if you're really that curious.

Josh: Wrong. That man must sleep with another woman, thus that woman also adds to the woman count while the men add too. It's actually really basic graph theory. *shrugs*



Edit: Similar issue summed up very well:

The same underlying issue has led to serious misinterpretations of other survey
data. For example, a few years ago, the Boston Globe ran a story on a survey of
the study habits of students on Boston area campuses. Their survey showed that on
average, minority students tended to study with non-minority students more than
the other way around. They went on at great length to explain why this “remarkable
phenomenon” might be true. But it’s not remarkable at all—using our graph theory
formulation, we can see that all it says is that there are fewer minority students than
non-minority students, which is, of course what “minority” means.


(Quoted from that book above.)


Edit 2: BTW, my bad on attributing "most scientific study ever" to the wrong source. It was ABC News not U of chicago.


Yep. Just ran it through my head again and you are right. :P

Eric

Eric Avatar



1,442


November 2005
Haven't read up on graph theory, but can't it be done like this:

Men Having Hetero Sex: 2.5 bil (no idea on actual numbers)
Women Having Hetero Sex: 2.5 bil

Men's Encounters: 17.5 bil
Women's Encounter: 17.5 bil

A man is reported as having sex with 40 women, and men's encounters are:
Men's Encounters: 17.5 bil + 40

That also means 40 women had sex with 1 more man, so:
Women's Encounters: 17.5bil + 1 * 40

So it always balances out?

Edit: Just thought I'd add that I know that the population won't be even, so if there is a difference in averages, it is due to only the population and not the sum of the encounters.


Last Edit: Oct 27, 2010 21:20:40 GMT by Eric

Chris

Chris Avatar

******
Head Coder

19,519


June 2005
Eric: Pretty much right. :) Yeah the averages vary slightly according to population, but either way, that still clearly disproves the "accurate" study. :P

newBookmarkLockedFalling