Hi Lori,
First you should look for missing values, outliers in your data and so on.
Depending on what you want to do next, you can take a look at the way the 50
variables discriminate in groups and at the loadings of each variable on the
factors extracted. Also, look at the total variance explained by factors.
About the easy way to run all possible bi-variate scatterplots without
typing in every combination, take a look at Ray's site:
http://www.spsstools.net/Syntax/Combinations/FindAllCombinationsOfNitemsOutOfMitems.txtit is a very good example and it's very easy to use, all you have to do is
replace in the last macro the "npar tests" command with your "scatterplots"
command.
Hth,
Vlad
On Fri, Jul 18, 2008 at 5:17 AM, Lori Day <
[hidden email]> wrote:
> Hello,
>
> This may be a basic question, but I am running exploratory factor
> analysis and getting stuck checking the assumption of linearity. I
> have 50 variables that are being put into the analysis and my
> understanding is that I want to run scatterplots of every possible
> pair of variables to see if they are linear. The first few I ran were
> not, so my first question is what do I do now? Secondly, is there an
> easy way to have SPSS run all the possible bi-variate scatterplots
> without typing in every combination?
>
> I appreciate your help!
> LD
>
> =====================
> 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
>
=====================
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
Locked
