Quote:
Originally Posted by sirbruce
Just because it's not a random sample doesn't mean it's useless. First, you'd have to posit a good theory why the self-selected website responses would be different from random. Then, you'd have to show how that difference would be statistically signifigant. And even then, a large difference wouldn't invalidate broad conclusions. We can be reasonably confident that it's not 80% under the age of 40, for example.
|
You haven't taken a statistics course have you?
Quote:
Originally Posted by sirbruce
First, you'd have to posit a good theory why the self-selected website responses would be different from random.
|
Self-selecting sites are by definition different from random. If they were the same as random, they wouldn't be self-selecting.