
hypersecant(link.theta="elogit", earg=if(link.theta=="elogit")
list(min=-pi/2, max=pi/2) else list(), init.theta=NULL)
hypersecant.1(link.theta="elogit", earg=if(link.theta=="elogit")
list(min=-pi/2, max=pi/2) else list(), init.theta=NULL)
Links
for more choices.earg
in Links
for general information."vglmff"
(see vglmff-class
).
The object is used by modelling functions such as vglm
,
and vgam
. Another parameterization is used for hypersecant.1()
.
This uses
For both parameterizations Newton-Raphson is same as Fisher scoring.
elogit
.x = rnorm(n <- 200)
y = rnorm(n) # Not very good data!
fit = vglm(y ~ x, hypersecant, trace=TRUE, crit="c")
coef(fit, matrix=TRUE)
fit@misc$earg
# Not recommended
fit = vglm(y ~ x, hypersecant(link="identity"), trace=TRUE, crit="c")
coef(fit, matrix=TRUE)
fit@misc$earg
Run the code above in your browser using DataLab