
Last chance! 50% off unlimited learning
Sale ends in
Computes the Complementary-log Transformation, Including its Inverse and the First Two Derivatives.
logc(theta, bvalue = NULL, inverse = FALSE, deriv = 0,
short = TRUE, tag = FALSE)
Numeric or character. See below for further details.
See Links
.
Details at Links
.
For deriv = 0
, the log of theta
, i.e.,
log(1-theta)
when inverse = FALSE
,
and if inverse = TRUE
then
1-exp(theta)
.
For deriv = 1
, then the function returns
d eta
/ d theta
as a function of theta
if inverse = FALSE
,
else if inverse = TRUE
then it returns the reciprocal.
Here, all logarithms are natural logarithms, i.e., to base e.
The complementary-log link function is suitable for parameters that
are less than unity.
Numerical values of theta
close to 1 or out of range
result in
Inf
, -Inf
, NA
or NaN
.
McCullagh, P. and Nelder, J. A. (1989) Generalized Linear Models, 2nd ed. London: Chapman & Hall.
# NOT RUN {
logc(seq(-0.2, 1.1, by = 0.1)) # Has NAs
# }
# NOT RUN {
logc(seq(-0.2, 1.1, by = 0.1), bvalue = 1 - .Machine$double.eps) # Has no NAs
# }
Run the code above in your browser using DataLab