StATS: Nonlinear Least Squares in S-plus and R (June 28, 2004).

I've worked on a brief explanation of how to fit an S-shaped curve using SPSS and someone wanted to know how to do this in S-plus. Here's a simple example.

xc <- c(0.8,0.5,0.2,-0.2,-0.5,-0.8)
yn <- c(0.02,0.10,0.29,0.20,0.80,1.00)
nls.mod1 <- nls(yn~1/(1+exp(b*xc-a)),start=list(a=0,b=10))

Formula: yn ~ 1/(1 + exp(b * xc - a))

     Value Std. Error t value
a -2.70380     1.4019 -1.92867
b  7.90714     3.7126  2.12981

Residual standard error: 0.149848 on 4 degrees of freedom

Correlation of Parameter Estimates:
b -0.908

x.grid <- seq(-1,1,by=0.01)


This same code should also work in R.

This page was written by Steve Simon while working at Children's Mercy Hospital. Although I do not hold the copyright for this material, I am reproducing it here as a service, as it is no longer available on the Children's Mercy Hospital website. Need more information? I have a page with general help resources. You can also browse for pages similar to this one at Category: Nonlinear regression.