[Corpora-List] significant differences between corpora

[Tina Waldman]

Dear All,

I am using chi square test to see if there is a significant difference between frequency of collocation occurrence in two corpora.

In corpus A there are 1,959 collocations in 250,000 words (standardized)

In corpus B ther are 939 collocations in 250,000 words (standardized)

My problem is with only two variables, I can't figure out how to run the test to show me if there is a difference between groups. I am not interested in seeing if the frequency of occurence of collocations is significant for a particular corpus. 

Any comments would be helpful.

Tina Waldman
Haifa University
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.linguistlist.org/pipermail/corpora/attachments/20070210/94e1c60f/attachment.htm>