LP_for_rev_fit {Petersen} | R Documentation |
Fit a combined FORWARD and REVERSE simple Lincoln-Petersen Model using pseudo-likelihood
Description
EXPERIMENTAL. This will take a data frame of capture histories, frequencies, and additional covariates (e.g., strata and/or continuous covariates) for a simple forward Petersen estimate plus estimates of escapement and associated stock proportions with SE for backwards estimation. DO NOT USE YET.
Usage
LP_for_rev_fit(
data,
E,
E.SE,
G,
G.SE,
min.G = 0.01,
n.boot = 100,
trace = FALSE
)
Arguments
data |
Data frame containing the variables:
plus any other covariates (e.g. discrete strata and/or continuous covariates) to be used in the model fitting. |
E |
Escapement at one or more terminal areas. E, E.SE, G, G.SE must all have the same length |
E.SE |
SE of the estimates of escapement |
G |
Estimated proportion of the stock at the first capture location estimated using GSI and other methods |
G.SE |
SE of the estimated stock proportion. |
min.G |
Miniumum acceptable stock proportion during the bootstrap estimation of uncertainty |
n.boot |
Number of bootstrap samples used to estimate the uncertainty |
trace |
Should intermediate tracing be enabled (e.g. browser() stops) |
Details
The frequency variable (freq
in the data
argument) is the number of animals with the corresponding capture history.
Capture histories (cap_hist
in the data
argument) are character values of length 2.
-
10 Animals tagged but never seen again.
-
11 Animals tagged and recaptured and tag present at event 2.
-
01 Animals captured at event 2 that appear to be untagged.
A pseudo-likelihood is constructed consisting of the usual likelihood for a forward capture recapture and marginal likelihoods for each of the escapement (E) and stock proportions (G) point estimates. I have not integrated over the uncertainty in G and E.
Value
An list object of class LP_for_rev_est with abundance estimates and measures of uncertainty
-
summary A data frame with the pseudo-likelihood value, abundance estimates and SE
-
data A data frame with the raw data used in the fit
-
fit Results of the fit from the optimizer
-
datetime Date and time the fit was done
Unlike other routine, it is not necessary to use a XX_est() function to get estimates of abundance.
Author(s)
Schwarz, C. J. cschwarz.stat.sfu.ca@gmail.com.
Examples
# Example of combined forward and reverse MR
# get some data
n1 <- 500
n2 <- 1500
m2 <- 150
f.data <- data.frame(cap_hist=c("10","11","01"), freq=c(n1 - m2, m2, n2 - m2))
f.data
E = 1500
E.SE = 150
G = .2
G.SE = .05
res <- LP_for_rev_fit(data=f.data,
E=E,
E.SE=E.SE,
G=G,
G.SE=G.SE)