Return to tldreport Forum - Message Thread - FAQ
Username: |
kristopher |
Date/Time: |
Sun, November 12, 2000 at 8:47 AM GMT |
Browser: |
Netscape Communicator V4.76 using Windows 98 |
Score: |
5 |
Subject: |
Statistics |
Message: |
|
>Do you know statistics? A sample of 1% can show the general trends and shares
of the whole 100%. Inside this 1% sample, if 90% is favorable to IOD and 10% is against
IOD, you can be sure that in the whole 100% there will be similar shares - similar
means 85% or 94% or something near 90%.<This is again quite funny, since I took
a few statistics classes in college and although I'm not a mathematical genius, what
you say above is absolute hogwash. A sample of 1% CAN show general trends, but this
is highly unlikely and is not a statistical rule. You cannot take 500 people from
an Internet forum and say that the statistical trends seen amongst those 500 people
represent the statistical trends of millions of users. This is further complicated
by the fact that nearly everybody here has some knowledge of the situtation, whereas
only a miniscule percentage OF a percentage of the Internet population even knows
what's going on here. A good example: I could go to Los Angeles, California and
survey 1000 people on whether they prefer the East Coast of the USA or the West Coast
of the USA. If 90% of the people say they prefer the West Coast and 10% prefer the
East Coast, can I assume that this is the same across the entire United States? Absolutely
not! Not only is the sample size too small, it is an unrepresentative sample group!
That's exactly what we have here. I can see that you obviously haven't taken any
statistics classes, or if you did, you didn't pay very good attention. Regards, Kristopher
Ross from USA (like that tells you anything useful)
|
| |
Link: |
The Cartoon Guide to Statistics |
Message Thread:
Privacy Policy | Terms of Service | Cookies Policy