Displaying 1 result from an estimated 1 matches for "sslogarithm".
Did you mean:
logarithm
2008 Aug 29
1
nls() fails on a simple exponential fit, when lm() gets it right?
...tedXyData(mCall[["x"]],LHS,data)
aaa=0.01 #Just guess aaa=0.01 to start the fit
bbb=min(xy$y) #Use the minimum y value as an initial guess for bbb
value=c(aaa,bbb)
names(value)=mCall[c("aaa","bbb")]
return(value)
}
fmla=as.formula("~(aaa*log(x)+bbb)")
SSlogarithmic=selfStart(fmla,initial=logarithmicInit,parameters=c("aaa","bbb"))
exponenInit=function(mCall,LHS,data) {
xy=sortedXyData(mCall[["x"]],LHS,data)
r=0.01 #Just guess r=0.01 to start the fit
A=min(xy$y) #Use the minimum y value as an initial guess for A
value=c(...