Perhaps simply a precision-weighted mean of the within animal means.
On Thu, 2 Jan 2003, Kate wrote:
> Yes. Also no 'treatment' here. Just have a collection
> of measures made during 'routine physicals' on these
> animals, different numbers of measures per animal,
> data set in the long form, and want to take a stab at
> stating what are 'normal' values--the mean, sd, also
> MEDIAN, etc--for this animal.
>
> "FEIVESON, ALAN H. (AL) (JSC-SD) (NASA)" wrote:
> >
> > Kate,
> >
> > Nick suggests we don't have enough information to
> properly answer your
> > questiion.
> > I would like to add that specifically, we need to
> know:
> >
> > a) but what sort of model for your data you are
> assuming
> > b) what paarameters in the model you are trying to
> estimate. I'll take a
> > guess:
> >
> > a) y_ij = mu + a_i + e_ij = j-th measurement on i-th
> animal
> >
> > mu is mean creatinine level for a population of
> animals undergoing (this)
> > experiment
> > mu + a_i is mean creatinine level specific to the
> i-th animal
> > a_i ~ N(0,siga^2)
> > e_ij is random variation of measured creatinine
> level about the mean for the
> > i-th animal
> > e_ij ~ N(0, sige^2)
> >
> > b) you wish to estimate mu and siga
> >
> > Is this correct? - If not - please give your
> interpretation of what a) and
> > b) are.
> >
> > Al Feiveson
> >
> > -----Original Message-----
> > From: Nick Cox [mailto:[email protected]]
> > Sent: Thursday, January 02, 2003 8:29 AM
> > To: [email protected]
> > Subject: st: RE: mean and median with multiple
> measures
> >
> > Kate
> >
> > > I have about 200 measures of creatinine but they
> are
> > > from only 25 animals. How do I calculate the mean
> and
> > > the median creatinine values in Stata?
> >
> > Several answers already; but if they don't
> > provide an answer I think you will need
> > to tell us more about your data structure.
> > What variables and what observations do
> > you have?
> >
> > Nick
> > [email protected]
> >
>
>
> __________________________________________________
> Do you Yahoo!?
> Yahoo! Mail Plus - Powerful. Affordable. Sign up now.
> http://mailplus.yahoo.com
> *
> * 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/
>
*
* 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/
