Absolutely.  DO they?  We'd like to think not. But besides the possibility
of stratification and clustering biases, it's certainly within the realm of
possibility to word a question in a leading manner.

I suspect that Gallup is generally better than that, but I haven't made any
effort to examine their questions.  (You can bet I will now.)

I challenge TIPSters to keep a critical eye on poll questioning (even not
from Gallup), and let's see what we can find.

Beth Benoit
University System of New Hampshire

> Ok, so I guess I was thinking along the lines of sampling--can it be possible
> to bias a random sample with some creative stratification and clustering?
> 
> Annette
> 
> Annette Kujawski Taylor, Ph.D.
> Associate Professor of Psychology
> University of San Diego


---
You are currently subscribed to tips as: [EMAIL PROTECTED]
To unsubscribe send a blank email to [EMAIL PROTECTED]

Reply via email to