Your report here boils down to "figures appear incorrect" without either
_complete_ code or _complete_ examples with both data and results.
I suggest you follow the guidelines at
http://www.stata.com/support/faqs/techsup/sendout.html
and liaise directly with Stata tech-support; otherwise there
is unlikely to be enough for anyone to work on here.
Nick
[email protected]
Roberto Melotti
I have been using PKSHAPE to reshape data for a 3X3 crossover trial.
I have data originally arranged by period for the 6 periods of the trial
(i.e. 1=baseline, 2=period 2, 3=1st wash-out, etc.)
I have seq (variable for sequence) coded as string of the type '0a0b0c'
I have pk-reshaped the dataset to obtain a long format dataset in order
to be used by the command PKCROSS.
namely I typed: pkshape id seq phv1 phv2 phv3 phv4 phv5 phv6,
outcome(phv)
I have saved the results in a new dataset and repeated the same command
for another outcome (phn); saved results in another dataset as well.
I have then merged together the two datasets matching by id and
sequence.
I have therefore run the command pkcross on each outcome variable
separately and everything seemed to work fine (the PKCROSS output is
straightforward).
Nonetheless when I tried to calculate the averages and standard
deviations for each outcome by treatment (with the command table), the
figures appear incorrect!
I have checked this with the averages on the outcome variable by period,
sequence and in such instance the problem doesn't occur: the estimates
are corrrect!
Has anyone else experienced the same problem?
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
