Print

Print


*****  To join INSNA, visit http://www.insna.org  *****


Hi Rick,
You can correlate matrices using QAP in UCINET under Tools | Testing Hypothesis | Dyadic QAP. 

You
can also find multiple measures of similarity  in UCINET under Tools |
Similarities (options include Pearson, Jaccard, Cross-products,
hamming-sim, etc.) and dissimilarity under Tools | Dissimilarities.


Hope this helps
Dan Halgin
University of Kentucky
[log in to unmask]


--------
I anticipate collecting data from a card sorting exercise
that will be in the form of a one mode matrix, where individual cells
show how often the row and column cards have been sorted into the same
category(pile) by a respondent


This exercise will be carried out with multiple participants, so there will be multiple versions of this matrix

With
UCINET (or any other tool) is there any way to identify the extent to
which the contents of any two matrices correlate with each other?
(which would then enable me to create an actors x actors matrix, where
each cell value showed how similar the card sorting results generated
by the respective row and column actors were)


regards, rick davies 		 	   		  
_____________________________________________________________________
SOCNET is a service of INSNA, the professional association for social
network researchers (http://www.insna.org). To unsubscribe, send
an email message to [log in to unmask] containing the line
UNSUBSCRIBE SOCNET in the body of the message.