snopes.com  

Go Back   snopes.com > Non-UL Chat > NFBSK Gone Wild!

Reply
 
Thread Tools Display Modes
  #41  
Old 18 April 2014, 11:50 PM
Chloe's Avatar
Chloe Chloe is offline
 
Join Date: 13 September 2004
Location: Kentucky
Posts: 39,316
Default

Quite elderly data, though. What did it mean to go on a date in the 1970's? Perhaps not the same as today.
Reply With Quote
  #42  
Old 19 April 2014, 12:08 AM
Lainie's Avatar
Lainie Lainie is offline
 
Join Date: 29 August 2005
Location: Suburban Columbus, OH
Posts: 74,585
Default

Quote:
Originally Posted by Steve View Post
I know this isn't the main point, but next time someone tells me they have trouble getting dates I'm definitely mentioning this finding:
I wouldn't recommend that.
Reply With Quote
  #43  
Old 19 April 2014, 12:10 AM
jimmy101_again jimmy101_again is offline
 
Join Date: 29 December 2005
Location: Greenwood, IN
Posts: 6,912
Default

Quote:
Originally Posted by Ryda Wong, EBfCo. View Post
Not to mention, 25% is quite statistically significant.
Is it? My stats are a bit rusty but a population of 12/16 compared to 16/16 has a student's t-test of 0.03, which is not "quite statistically significant". It is the significance level that says "you don't know, you need another study".

Which is more statistically significant 12/16 women successful or 0/16 men successful? (Hint, the male response is much more statistically significant.) Besides, often statistical significance is irrelevant and practical significance is much more important. A scientific study that finds a particular population is 5% more likely of developing a disease really doesn't represent a practical significance (even if the 5% is statistically significant).
Reply With Quote
  #44  
Old 19 April 2014, 01:25 AM
me, no really's Avatar
me, no really me, no really is offline
 
Join Date: 02 June 2005
Location: Brisbane, Australia
Posts: 2,550
Default

I have no dog in the fight either way, but significance level of 0.05 is usually taken as the threshold for statistically significant. As such, 0.03 is definitely significant. Of course, the way science works, you still need another study - even with significant results.
Reply With Quote
  #45  
Old 19 April 2014, 02:16 AM
Steve Steve is offline
 
Join Date: 19 October 2002
Location: Charleston, SC
Posts: 4,906
Default

Since .03 is less than .05, I'm not quite sure what you mean. Why would something below the significance level be significant?
Reply With Quote
  #46  
Old 19 April 2014, 02:29 AM
erwins's Avatar
erwins erwins is offline
 
Join Date: 04 April 2006
Location: Portland, OR
Posts: 12,367
Default

Quote:
Originally Posted by Steve View Post
Since .03 is less than .05, I'm not quite sure what you mean. Why would something below the significance level be significant?
Because lower is considered significant, and higher is not.
Reply With Quote
  #47  
Old 19 April 2014, 02:31 AM
Steve Steve is offline
 
Join Date: 19 October 2002
Location: Charleston, SC
Posts: 4,906
Default

D'oh. Of course, you and me, no really are right. Yeah, carry on.
Reply With Quote
  #48  
Old 19 April 2014, 05:22 PM
jimmy101_again jimmy101_again is offline
 
Join Date: 29 December 2005
Location: Greenwood, IN
Posts: 6,912
Default

Quote:
Originally Posted by Steve View Post
Since .03 is less than .05, I'm not quite sure what you mean. Why would something below the significance level be significant?
"Significance" is calculated backwards. P less then 0.05 is the rule of thumb for the cutoff of statistical significance. If P>0.05 then the difference is not "statistically significant". If P<0.05 it is "statistically significant". A P=0.05 means there is a 1 in twenty chance that the observed difference occurred by random chance and a 19 in 20 chance that the difference is due to something other than random noise and the vagaries of choosing from a population.

However, the 0.05 cutoff for significance, though widely used, is completely arbitrary. Why isn't the arbitrary cutoff 0.10 (1 in 10 chance) or 0.01 (1 in 100 chance)?

A P value of 0.03 is considered significant but the significance is pretty weak (there is a 3% chance that the observed difference isn't real).
Reply With Quote
  #49  
Old 19 April 2014, 06:04 PM
Amigone201's Avatar
Amigone201 Amigone201 is offline
 
Join Date: 11 March 2005
Location: Islip, NY
Posts: 6,040
Default

Quote:
Originally Posted by Chloe View Post
And it's frustrating, because you could easily strip out the hyperbole and have something worth discussing. I guess sometimes people would rather be controversial than accurate.
Because it's more fun to be angry than to be correct. See: Exhibit A, comments on news articles.

I've said it before and I'll say it again: Having a proper, effective, and worthwhile debate is boring.
Reply With Quote
  #50  
Old 19 April 2014, 06:05 PM
Mickey Blue's Avatar
Mickey Blue Mickey Blue is offline
 
Join Date: 01 February 2004
Location: Oregon
Posts: 17,571
Default

If we wanted rational, calm, worthwhile debates we wouldn't label one another as 'pro abortion' or 'anti-woman'. Hard not to let emotion (or in the cast of the OP probably a desire for humor or overstatement) get in the way of what we are saying.
Reply With Quote
  #51  
Old 19 April 2014, 09:48 PM
Esprise Me's Avatar
Esprise Me Esprise Me is offline
 
Join Date: 02 October 2005
Location: Los Angeles, CA
Posts: 6,946
Default

Quote:
Originally Posted by Amigone201 View Post
Having a proper, effective, and worthwhile debate is boring.
Maybe to some people, but there are plenty of people in this world who enjoy it.
Reply With Quote
Reply

Thread Tools
Display Modes

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is On

Forum Jump

Similar Threads
Thread Thread Starter Forum Replies Last Post
Four people - including two infants - found dead inside Arlington, Mass., home snopes Police Blotter 0 18 November 2013 09:26 PM
Message From God Found Hidden Inside DNA Sequence hambubba Fun House 12 21 May 2013 08:02 AM
Deep Inside: A Study of 10,000 Porn Stars and Their Careers snopes NFBSK Gone Wild! 0 23 February 2013 06:21 PM
Study backs cops: Cold weather keeps bad guys inside snopes Crime 1 10 February 2009 04:08 AM
9-Year-Old Girl's Twin Is Found Inside Her Stomach snopes Medical 9 12 June 2008 11:34 PM


All times are GMT. The time now is 12:24 AM.


Powered by vBulletin® Version 3.8.7
Copyright ©2000 - 2019, vBulletin Solutions, Inc.