R help - Apr 2001 - noise in explanatory variable. Used to be: Regressions with monot onicity constraints

Dear All, First of all let me thank Frank Harrell, Thomas Lumley and Greg
Snow for their very helpful insights on fitting monotonic regressions.

As I work with my data I often feel like the data "resists" to fit
monotonic
model though I have a strong a-priory believe it should.
One of potential reasons of this resistance is that the explanotary variable
is not known exactly rather has a noice term of its own. That is instead of
fitting the 
y = f(x) + noise
model I need to fit
y = f(x + noise2) + noise
where f() is either monotonic or smooth (I hope that if I allow for noise in
x then estimated smooth f() will naturally come out monotonic).

Is it a known setting of a statistical model?
Is there S-Plus/R/C code for fitting such models?

Thank you,
Vadim
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
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
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._