[R] Sub_scribe and a question

[Peter Dalgaard BSA]

"Philippe Grosjean" <phgrosje at ulb.ac.be> writes:

> Hello,
> 
> I would do like this: if the slope is a, and it is perfectly known, just
> substract a*x from y. If you assume a relationship like y = a*x + b +
> epsylon with epsylon having a normal distribution (0, sigma), then, y - a*x
> should have a normal distribution (b, sigma), and the mean value of computed
> y - a*x should simply be a good estimate of b, the intercept you are looking
> for.
> 

..or as a generic solution, use y~offset(a*x). This has the advantage
of working with generalized linear models as well.

-- 
   O__  ---- Peter Dalgaard             Blegdamsvej 3  
  c/ /'_ --- Dept. of Biostatistics     2200 Cph. N   
 (*) \(*) -- University of Copenhagen   Denmark      Ph: (+45) 35327918
~~~~~~~~~~ - (p.dalgaard at biostat.ku.dk)             FAX: (+45) 35327907
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._