IBM Click Here!
| Navigational map -- for text only please go to the bottom of the page ||Forums|
Readers' Choice Awards (siteadm) Fri, 13 Jun
What Poll? (forum) Sat, 14 Jun
Another poll was held?? (up_yours) Mon, 16 Jun
Big Name Computer Company (rparker) Mon, 16 Jun
Rubbish!!! (Yaztromo) Mon, 16 Jun
Yes, I call it valid (rparker) Mon, 16 Jun
IT Vendors (EdSeitzinger) Thu, 19 Jun
Gee since you are a consultant... (Alan Laing) Thu, 19 Jun
Consultant with a brain (EdSeitzinger) Thu, 19 Jun
Re: Consultant with a brain (shifrbv) Today

Math

Posted by: w nau
Date posted: Fri Jun 20 6:29:48 PDT 1997

And I also have a brain and a Finance degree, and can realize that a sample size of less than 1% of the population is statistically invalid......
Er, it was less than 0.1%. It also wasn't random.
Any second college student in Math or Business could tell you this.....
Yup.

Now, I confess to being pretty good at math, but knowing very little about stats. My concern isn't so much the percentage, but rather the minimum. Suppose your entire audience was 5000 people (a small city). Would sampling five (first eliminating a major portion of them) be a valid sample? Of course not. There needs to be a minimum number. On the other hand if they had a sample of 100 million people by "randomly" contacting 100,000, I don't think anyone would have a problem.

Where is the breaking point? I really don't know, but I do know that it's above five and below 100,000. 300 is in there, but I don't know if it's good enough.

Respond | Search | Help


For questions or comments, email the Forums Editor

kristin_kueter@infoworld.com