Displaying 2 results from an estimated 2 matches for "residus".
Did you mean:
resides
2005 Nov 13
4
Robust Non-linear Regression
...www.graphpad.com/articles/RobustNonlinearRegression_files/frame.htm
<http://www.graphpad.com/articles/RobustNonlinearRegression_files/frame.htm>
in short: instead of using the premise that the residuals are gaussian they
propose a Lorentzian distribution,
in stead of minimizing the squared residus SUM (Y-Yhat)^2, the objective
function is now
SUM log(1+(Y-Yhat)^2/ RobustSD)
where RobustSD is the 68th percentile of the absolute value of the residues
my question is: is there a smart and elegant way to change to objective
function from squared Distance to log(1+D^2/Rsd^2) ?
or alternative...
2002 Jul 02
1
subscript out of bounds
...rstand where I'm wrong because the functions in MyStuff
individually work well when I just paste them from my editor.
Thanks for any help
Fred
Linux debian potato
R 1.5.0
here below, the file MyStuff
-----------------------------
"adjresid" <- function(tab) {
# calcul des residus normes sur un tableau de contingence
# adjusted Pearson residuals
# Brett Presnell <presnell at stat.ufl.edu>
#
tot <- sum(tab)
rp <- apply(tab, 1, sum) / tot
cp <- apply(tab, 2, sum) / tot
mu <- tot * ( rp %o% cp )
norm(tab - mu) / sqrt( mu * ( (1 - rp) %o...