R2admb (version 0.7.10)

AIC.admb: Standard accessor functions for ADMB model fits

Description

Extract standard information such as log-likelihood, AIC, coefficients, etc. from ADMB model fits

Usage

## S3 method for class 'admb':
AIC(object, ..., k = 2)

  ## S3 method for class 'admb':
confint(object, parm, level = 0.95,
    method = "default", type = "fixed", ...)

  ## S3 method for class 'admb':
print(x, verbose = FALSE, ...)

  ## S3 method for class 'admb':
summary(object, correlation = FALSE,
    symbolic.cor = FALSE, ...)

  ## S3 method for class 'summary.admb':
print(x,
    digits = max(3, getOption("digits") - 3),
    symbolic.cor = x$symbolic.cor,
    signif.stars = getOption("show.signif.stars"), ...)

  ## S3 method for class 'admb':
logLik(object, ...)

  ## S3 method for class 'admb':
coef(object, type = "fixed", ...)

  ## S3 method for class 'admb':
vcov(object, type = "fixed", ...)

  stdEr(object, ...)

  ## S3 method for class 'admb':
stdEr(object, type = "fixed", ...)

  ## S3 method for class 'admb':
deviance(object, ...)

Arguments

x

an ADMB model fit (of class "admb")

object

an ADMB model fit (of class "admb")

k

penalty value for AIC fits

type

which type of parameters to report. Character vector, including one or more of "fixed" or "par" (standard, fixed-effect parameters); "random" (random effect parameters); "rep" (report variables); "sdrpt" (sdreport variables); "extra" (report a

parm

(currently ignored: FIXME) select parameters

level

alpha level for confidence interval

method

(character): "default" or "quad", quadratic (Wald) intervals based on approximate standard errors; "profile", profile CIs (if profile was computed); "quantile", CIs based on quantiles of the MCMC-generated posterior density (if MCMC was comput

correlation

currently unused parameter

symbolic.cor

currently unused parameter

verbose

show messages

...

other parameters (for S3 generic compatibility)

digits

number of digits to display

signif.stars

show significance stars?

Value

• Extracts appropriate values: numeric (scalar) for AIC, type logLik for logLik, numeric vector of coefficients, numeric variance-covariance matrix of parameter estimates

Examples

admbex <- system.file("doc","Reedfrog_runs.RData",package="R2admb")
 load(admbex)
 m1
 coef(m1)
 summary(m1)
 coef(summary(m1)) ## returns just z-table
 AIC(m1)
 vcov(m1)
 logLik(m1)
 deviance(m1)
 stdEr(m1)