Skip to contents

Confidence intervals for model parameters

Usage

# S3 method for class 'galamm'
confint(object, parm, level = 0.95, method = "Wald", ...)

Arguments

object

An object of class galamm returned from galamm.

parm

Parameters for which to compute intervals. Use "theta" to get all variance parameters, "beta" to get all fixed regression coefficients, "lambda" to get all factor loadings, and "weights" to get all weights. The parameter can also be given as a numeric vector with indices specifying the parameters. When given as characters, the arguments are case sensitive.

level

Decimal number specifying the confidence level. Defaults to 0.95.

method

Character of length one specifying the type of confidence interval. Currently only "Wald" is available. The argument is case sensitive.

...

Other arguments passed on to other methods. Currently not used.

Value

A matrix with the requested confidence intervals.

See also

fixef.galamm() for fixed effects, coef.galamm() for coefficients more generally, and vcov.galamm() for the variance-covariance matrix. confint() is the generic function.

Other details of model fit: VarCorr(), coef.galamm(), deviance.galamm(), factor_loadings.galamm(), family.galamm(), fitted.galamm(), fixef(), formula.galamm(), llikAIC(), logLik.galamm(), nobs.galamm(), predict.galamm(), print.VarCorr.galamm(), ranef.galamm(), residuals.galamm(), response(), sigma.galamm(), vcov.galamm()

Examples

# Poisson GLMM
count_mod <- galamm(
  formula = y ~ lbas * treat + lage + v4 + (1 | subj),
  data = epilep, family = poisson
)

confint(count_mod, parm = "beta", level = .99)
#>                  0.5 %      99.5 %
#> (Intercept)  1.5239392  2.06319914
#> lbas         0.5471847  1.22182317
#> treat       -0.7155511  0.04562592
#> lage        -0.4081356  1.37730585
#> v4          -0.3016653 -0.02050959
#> lbas:treat  -0.1843249  0.86110474