profile-methods {bbmle} | R Documentation |
Create likelihood profiles for a fitted model
## S4 method for signature 'mle2': profile(fitted, which = 1:p, maxsteps = 100, alpha = 0.01, zmax = sqrt(qchisq(1 - alpha/2, p)), del = zmax/5, trace = FALSE, skiperrs=TRUE, tol.newmin = 0.001, ...)
fitted |
A fitted maximum likelihood model of class “mle2” |
which |
a numeric or character vector describing which parameters to profile (default is to profile all parameters) |
maxsteps |
maximum number of steps to take looking for an upper value of the negative log-likelihood |
alpha |
maximum confidence level |
zmax |
maximum value of negative log-likelihood (default is the likelihood ratio test critical value corresponding to a 2-tailed chi-squared test at level alpha) |
del |
step size for profiling |
trace |
(logical) produce tracing output? |
skiperrs |
(logical) ignore errors produced during profiling? |
tol.newmin |
tolerance for finding a new minimum below the minimum negative log-likelihood estimated in initial fit |
... |
not used |
The profiling process starts out by ...