Hullo,
*------------------------------------------------------------------------------.
I am trying to analyze data from the following experimental design in which
144 subjects responded (0 OR 1) to 100 trials each (total data points = 14,400).
I have three nominal IVs of interest: ALTTYPE & BR (both coded 1,2,3) and LAST
(coded 0,1). I am using GENLINMIXED and having problems.
The analysis runs without error but I am getting a strange warning:
"DATA_STRUCTURE:One or more subject fields were specified but not actually
used in the analysis."
The table of Fixed Effects prints F values for corrected model and both effects;
The df1 vals are correct, but all df2 vals are wrong (6) & the sig values are
.99ish. The dfs for the denominator(s) should be in the thousands.
The syntax is as follows.
VARIABLE LEVEL SUBID ALTTYPE LAST BR (NOMINAL).
GENLINMIXED /DATA_STRUCTURE SUBJECTS=SUBID
/FIELDS TARGET=RESP TRIALS=NONE OFFSET=NONE
/TARGET_OPTIONS DISTRIBUTION=BINOMIAL LINK=LOGIT REFERENCE=0
/FIXED EFFECTS= ALTTYPE BR LAST USE_INTERCEPT=TRUE
/BUILD_OPTIONS TARGET_CATEGORY_ORDER=ASCENDING INPUTS_CATEGORY_ORDER=DESCENDING.
Any suggestions?
Jason
*------------------------------------------------------------------------------.
_____________________________________________________________
Jason W. Beckstead, Ph.D.
Associate Professor/Quantitative Methodologist
University of South Florida College of Nursing
12901 Bruce B. Downs Blvd., MDC22, Tampa, FL 33612, USA
Statistical Editor, International Journal of Nursing Studies
phone: +1.813.974.7667 fax: +1.813.974.5418
personal website:
http://personal.health.usf.edu/jbeckste/
International Journal of Nursing Studies
http://www.elsevier.com/ijns
Locked
