bnlr {gnlm} | R Documentation |
bnlr
fits user-specified nonlinear regression equations to
binomial data with various link functions (logit
, probit
,
comp log log
, log log
, Cauchy
, Student t
,
stable
, or mixture
). The mixture link is a logistic link
with extra probability mass for y=0
and y=n
.
Nonlinear regression models can be supplied as formulae where
parameters are unknowns in which case factor variables cannot be used and
parameters must be scalars. (See finterp
.)
The printed output includes the -log likelihood (not the deviance), the corresponding AIC, the maximum likelihood estimates, standard errors, and correlations.
bnlr(y, link="logit", mu=NULL, linear=NULL, pmu=NULL, pshape=NULL, wt=1, envir=parent.frame(), print.level=0, typsiz=abs(p),ndigit=10, gradtol=0.00001, stepmax=10*sqrt(p%*%p), steptol=0.00001, iterlim=100, fscale=1)
y |
A two column matrix of binomial data or censored data or an
object of class, response (created by
restovec ) or repeated (created by
rmna or lvna ). If the
repeated data object contains more than one response variable,
give that object in envir and give the name of the response
variable to be used here. |
link |
A character string containing the name of the
link function. The Student t , stable , and mixture
links contain an unknown parameter to be estimated, respectively the
logarithm of the degrees of freedom, the tail parameter transformed by
log(tail/(2-tail)), and logit of the mixture probability, so that
they lie on the whole real line. |
mu |
A user-specified function of pmu , and possibly
linear , giving the regression equation for the location. This
may contain a linear part as the second argument to the function. It
may also be a formula beginning with ~, specifying either a linear
regression function for the location parameter in the Wilkinson and
Rogers notation or a general function with named unknown parameters.
If it contains unknown parameters, the keyword linear may be
used to specify a linear part. If nothing is supplied, the location is
taken to be constant unless the linear argument is given. |
linear |
A formula beginning with ~ in W&R notation, specifying the linear part of the regression function for the location parameter or list of two such expressions for the location and/or shape parameters. |
pmu |
Vector of initial estimates for the location parameters.
If mu is a formula with unknown parameters, their estimates
must be supplied either in their order of appearance in the expression
or in a named list. |
pshape |
If the link is Student t , an initial
estimate of the degrees of freedom; if it is stable , an
estimate of the tail parameter; if it is mixture , an estimate
of the mixture probability. |
wt |
Weight vector. |
envir |
Environment in which model formulae are to be
interpreted or a data object of class, repeated , tccov ,
or tvcov ; the name of the response variable should be given in
y . If y has class repeated , it is used as
the environment. |
others |
Arguments controlling nlm . |
A list of class gnlm
is returned that contains all of the
relevant information calculated, including error codes.
J.K. Lindsey
# assay to estimate LD50 y <- c(9,9,10,4,1,0,0) y <- cbind(y,10-y) dose <- log10(100/c(2.686,2.020,1.520,1.143,0.860,0.647,0.486)) summary(glm(y~dose, family=binomial)) bnlr(y, mu=~dose, pmu=c(1,1)) summary(glm(y~dose, family=binomial(link=probit))) bnlr(y, link="probit", mu=~dose, pmu=c(1,1)) bnlr(y, link="log log", mu=~dose, pmu=c(1,1)) bnlr(y, link="comp log log", mu=~dose, pmu=c(1,1)) bnlr(y, link="Cauchy", mu=~dose, pmu=c(60,-30)) bnlr(y, link="Student", mu=~dose, pmu=c(60,-30), pshape=0.1) bnlr(y, link="stable", mu=~dose, pmu=c(20,-15), pshape=0, stepmax=1) bnlr(y, link="mixture", mu=~dose, pmu=c(60,-30), pshape=-2.5) # mu <- function(p) -p[1]*(log10(p[2])-dose) bnlr(y, mu=mu, pmu=c(1,100)) bnlr(y, link="probit", mu=mu, pmu=c(1,100))