For a given set of parameters and data, it computes -2*log Likelihood value
but does not include data factorials. Factorials for unmarked are not needed
but are included in final result by js so the result matches
output from MARK for the POPAN model.
js.lnl(par, model_data, debug = FALSE, nobstot, jsenv)-log likelihood value, excluding data (ui) factorials which are added in js after optimization to match MARK
vector of parameter values
a list that contains: 1)imat-list of vectors and matrices constructed by
process.ch from the capture history data, 2)Phi.dm design matrix for Phi constructed by create.dm,
3)p.dm design matrix for p constructed by create.dm, 4)pent.dm design matrix for probability of entry constructed by create.dm,
5) N.dm design matrix for estimates of number of animals not caught from
super-population constructed by create.dm,
6)Phi.fixed matrix with 3 columns: ch number(i), occasion number(j),
fixed value(f) to fix phi(i,j)=f, 7) p.fixed matrix with 3 columns: ch number(i), occasion number(j),
8) pent.fixed matrix with 3 columns: ch number(i), occasion number(j), fixed value(f) to fix pent(i,j)=f, and
9) time.intervals intervals of time between occasions if not all 1
fixed value(f) to fix p(i,j)=f
if TRUE will printout values of par and function value
number of unique caught at least once by group if applicable
environment for js to update iteration counter
Jeff Laake
This functions uses cjs.lnl and then supplements with the
remaining calculations to compute the likelihood for the POPAN formulation
(Arnason and Schwarz 1996) of the Jolly-Seber model.
Schwarz, C. J., and A. N. Arnason. 1996. A general methodology for the analysis of capture-recapture experiments in open populations. Biometrics 52:860-873.