>
>I ran a SAS macro and output a tetrachoric correlation matrix of 236
>variables successfully. However, when I ran a factor analsyis using the
>matrix as the infile, it fails. Although I have specified 'corr' for
>_type_, SAS said that:
>
>"Data set WORK.MATRIX2 has _TYPE_ and _NAME_ variables but is not
>TYPE=ACE, CORR, COV, EST, FACTOR, SSCP, UCORR, or UCOV.
>
>ERROR: CORR matrix incomplete in data set WORK.MATRIX.
>
>The following is the SAS program. I would appreciate it if any SAS expert
>out there can give me a hand:
>
>data matrix (type=corr); infile "plcorr2.txt";
> _type_='corr';
>input _name_ $ as1-as24 bs1-bs24 cs1-cs25 ds1-ds25 es1-es25 fs1-fs25
>gs1-gs25 hs1-hs60;*/
>
>data matrix2; set matrix;
> proc factor data=matrix method = prinit scree;
>run;
>
>****************************************************************************
>Chong-ho (Alex) Yu, Ph.D., MCSE, CNE
>Academic Research Professional/Manager
>Educational Data Communication, Assessment, Research and Evaluation
>Farmer 418
>Arizona State University
>Tempe AZ 85287-0611
>Email: [EMAIL PROTECTED]
>URL:http://seamonkey.ed.asu.edu/~alex/
>****************************************************************************
>
>
I suspect the problem is that you are not inputting the full square correlation
matrix, including the 1's on the diagonal. You are only reading in 233
correlations per input statement, 3 short of 236.
In addition, your syntax is not clear.
>data matrix2; set matrix;
> proc factor data=matrix method = prinit scree;
>run;
>
The two statements:
data matrix2; set matrix;
simply create a copy of your file which is never used.
If you email me I would be willing to assist off-list (as this is propbably not
of general interest on this list). There is also the SAS-L mailing list which
is mirrored as the newsgroup
comp.soft-sys.sas
where there is lots excellent help available. I would highly recommend this
if you are going to be doing work with SAS.
Hope this helps,
Dan Nordlund
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
