weibull_link: Weibull link function with guessing and lapsing rates

In modelfree: Model-free estimation of a psychometric function

Description

Weibull link for use with GLM functions. The guessing rate and lapsing rate are fixed, and power parameter is set to be equal K, hence link is a function of only one variable

Usage

weibull_link( K, guessing = 0, lapsing = 0 )

Arguments

K	power parameter for reverse Weibull link function
guessing	guessing rate; default is 0
lapsing	lapsing rate; default is 0

Value

link	Weibull link for use in all GLM functions

Examples

data( "01_Miranda" )
x <- example01$x
r <- example01$r
m <- example01$m
glmdata <- data.frame( cbind( r/m ,m , x ) )
names( glmdata ) <- c( "resp", "m", "x" )
glmformula <- c( "resp ~ x" )
userlink<-weibull_link( 20 )
fit <- glm( glmformula, data = glmdata, weights = m, family = binomial( userlink ) )

Example output

Loading required package: PolynomF
Loading required package: SparseM

Attaching package: 'SparseM'

The following object is masked from 'package:base':

    backsolve

modelfree documentation built on May 2, 2019, 6:07 p.m.