use chi square for this analysis

[Talino Bruno]

I am using one measure that gives two separate scores (INT and EXT) . I did
frequency analysis for both INT and EXT and I added up  the number of
subject with scores above 60. what I would like to do is to see if there is
significant difference between the number that scored over 60 in the INT
scale to those WHO scored over 60 on the EXT scale. Would I use a chi
square test, if so which one specifically?

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

[Marta Garcia-Granero]

Talino Bruno wrote:
> I am using one measure that gives two separate scores (INT and EXT) . I did
> frequency analysis for both INT and EXT and I added up  the number of
> subject with scores above 60. what I would like to do is to see if there is
> significant difference between the number that scored over 60 in the INT
> scale to those WHO scored over 60 on the EXT scale. Would I use a chi
> square test, if so which one specifically?
>

If both variables have been measured in the same subjects, then you have
two paired binary variables: use McNemar test.

HTH,
Marta García-Granero

--
For miscellaneous statistical stuff, visit:
http://gjyp.nl/marta/

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD