On 29 Sep 2010, at 10:09 AM, Daniel Ezra Johnson wrote:
> To be fair, do you really often want to test the null hypothesis "all
> three (or more) of these variables are independent"? Why not look at
> individual 2-way relationships first?…
Well, sometimes, yes. Not often, though, you're right.
> …That's not to say there's no
> omnibus chi-square-like thing out there, I think in fact there
> probably is.
> Another thing - for X by Y contigency tables, don't you prefer
> Fisher's Exact Test?
That and Barnard's Exact Test, but yeah—when i use the chi-square it's
mainly 'cause it's easy and i have a lot more experience with it than
with anything else.
Very truly yours,
David Bowie
########################################################################
The Variationist List - discussion of everything related to variationist sociolinguistics.
To send messages to the VAR-L list (subscribers only), write to:
[log in to unmask]
To unsubscribe from the VAR-L list, click the following link:
http://jiscmail.ac.uk/cgi-bin/webadmin?SUBED1=VAR-L&A=1
|