Learn R Programming

drLumi (version 0.1.2)

SSl5cons: Self-Starting Nls 5 parameters logistic constraint regression model

Description

This selfStart model evaluates the 5 parameters logistic regression model and its gradient for the lower asymptote constraint method. It has an initial attribute that will evaluate initial estimates of the parameters hAsym, Slope, xMid and Asymetry for a given set of data Instead of the standard exp function this implementation use the 10^ function. $$f(x)=lAsym +\frac{hAsym-lAsym}{(1+10^{Slope(x-xMid)})^{Asymetry}}$$

Usage

SSl5cons(..constraint.value,x, Slope, hAsym, xMid, Asymetry)

Arguments

..constraint.value
a numeric value representing the lower asymptote when x trend to -Inf. In this function this value is not a parameter is just a numeric value to constraint lAsym parameter.
x
a numeric vector of values at which to evaluate the model
Slope
is a numeric parameter representing the -slope of the function at the inflection point
hAsym
a numeric parameter representing the higher asymptote when x trend to Inf
xMid
is the x value corresponding to the inflection point
Asymetry
is a numeric parameter representing the asymetry around the inflection point

Value

  • The value returned is a list containing the nonlinear function, the self starter function and the parameter names.

format

A selfStart model

Examples

Run this code
# Load data
data(ecdata)
data(mfidata)

# Select analyte FGF for plate 1
dat <- mfidata[mfidata$plate=="plate_1" & mfidata$analyte=="FGF",]

sdf <- data_selection(dat, ecdata)[[1]]

# SSl5
cons <- scluminex("plate_1",sdf$standard, sdf$background,
            lfct="SSl5",
            bkg="constraint",
            fmfi="mfi",
            verbose=FALSE)

summary(cons)

# Comparison constraint vs no constraint (same returning value but estimate
# 4 parameters).
lAsym <- 1
Slope <- 2
hAsym   <- 2
xMid <- 3
Asymetry <- 1.5

concentration <- 2
SSl5(concentration, Slope, lAsym, hAsym, xMid, Asymetry)
SSl5cons(lAsym, concentration, Slope, hAsym, xMid, Asymetry)

Run the code above in your browser using DataLab