FacebookTwitter
Hatrack River Forum Post New Topic  Post A Reply
my profile login | register | search | faq | forum home

  next oldest topic   next newest topic
» Hatrack River Forum » Active Forums » Books, Films, Food and Culture » A note on language and probability

   
Author Topic: A note on language and probability
Hobbes
Member
Member # 433

 - posted      Profile for Hobbes   Email Hobbes         Edit/Delete Post   Reply With Quote 
If I were to use the phrase: "...most people...", or "...the majority of people..." or perhaps even some percentage that fell below 100% that indicates that though you are more likely to find whatever I'm describing than not; there must be some examples of that not being the case. For instance, if I were to say: "Most professors are on the liberal end of the political spectrum", this is not effectively countered by a statement such as: "That's not true, I knew a professor once who kept trying to get me to join the Libertarian party." You see, the word 'most', like the word 'majority', indicates only one thing about the percentage: it's over 50. It does not mean 100%. If I wanted to give an absolute then I might use words like 'all', 'every', or even go right to the horse’s mouth and say 'one hundred percent'.

Thank-you.

Hobbes [Smile]

Posts: 10602 | Registered: Oct 1999  |  IP: Logged | Report this post to a Moderator
The White Whale
Member
Member # 6594

 - posted      Profile for The White Whale           Edit/Delete Post   Reply With Quote 
I think it should be based somewhat off of the IPCC reports, and how they deal with similar phrases: ( Link to a pdf of uncertainty and phrasing )

quote:
Table 4. Likelihood Scale.
Terminology Likelihood of the occurrence/outcome
Virtually certain: > 99% probability
Very likely: > 90% probability
Likely: > 66% probability
About as likely as not: 33 to 66% probability
Unlikely: < 33% probability
Very unlikely: < 10% probability
Exceptionally unlikely: < 1% probability

I propose:

all = 100%
most = > 75%
more than half = 50 - 75%
less than half = 25 - 50%
a few = < 25%
none = 0%

ETA: 50 - 75% really isn't less than half

Posts: 1710 | Registered: Jun 2004  |  IP: Logged | Report this post to a Moderator
Samprimary
Member
Member # 8561

 - posted      Profile for Samprimary   Email Samprimary         Edit/Delete Post   Reply With Quote 
Sounds like someone's been experiencing the super happy-fun-time experience of using data and watching people try to contradict it with anecdote!
Posts: 15417 | Registered: Aug 2005  |  IP: Logged | Report this post to a Moderator
Noemon
Member
Member # 1115

 - posted      Profile for Noemon   Email Noemon         Edit/Delete Post   Reply With Quote 
quote:
Originally posted by The White Whale:
I propose:

all = 100%
most = > 75%
more than half = 50 - 75%
less than half = 25 - 75%
a few = < 25%
none = 0%

That's potentially a very big half!
Posts: 16059 | Registered: Aug 2000  |  IP: Logged | Report this post to a Moderator
The White Whale
Member
Member # 6594

 - posted      Profile for The White Whale           Edit/Delete Post   Reply With Quote 
Fixed!
Posts: 1710 | Registered: Jun 2004  |  IP: Logged | Report this post to a Moderator
Mucus
Member
Member # 9735

 - posted      Profile for Mucus           Edit/Delete Post   Reply With Quote 
Personally, I use "most" as just > 50% rather than > 75%.

On the other hand, "few" can be rather fuzzily-defined. I'm not unsympathetic to wanting to define few as < 25% but I would note it would lead to sentences that may cause double-takes such as "there are few black people in the United States" or "there are few Muslims on Earth" and the like.

Posts: 7593 | Registered: Sep 2006  |  IP: Logged | Report this post to a Moderator
The White Whale
Member
Member # 6594

 - posted      Profile for The White Whale           Edit/Delete Post   Reply With Quote 
I think the IPCC was trying to find terms and phrases, and define them in such away, that these double-takes wouldn't happen. There was ambiguity in the definitions for the first reports, and that caused confusion and problems. By defining them like this, there should be less confusion.

And if the definition of few was well known to be less than 25%, then there wouldn't be double-takes.

Posts: 1710 | Registered: Jun 2004  |  IP: Logged | Report this post to a Moderator
Vyrus
Member
Member # 10525

 - posted      Profile for Vyrus   Email Vyrus         Edit/Delete Post   Reply With Quote 
Yes, and because everybody checks the IPCC reports along with the news and high-ranked political journals (as opposed to, say, youtube or myspace) this will be around in no time!

Well, at least WE know the truth.

(I think?)

Posts: 135 | Registered: Jun 2007  |  IP: Logged | Report this post to a Moderator
   

Quick Reply
Message:

HTML is not enabled.
UBB Code™ is enabled.
UBB Code™ Images not permitted.
Instant Graemlins
   


Post New Topic  Post A Reply Close Topic   Feature Topic   Move Topic   Delete Topic next oldest topic   next newest topic
 - Printer-friendly view of this topic
Hop To:


Contact Us | Hatrack River Home Page

Copyright © 2008 Hatrack River Enterprises Inc. All rights reserved.
Reproduction in whole or in part without permission is prohibited.


Powered by Infopop Corporation
UBB.classic™ 6.7.2