logLik
extracts the log-likelihood (exact or approximated).
get_any_IC
and AIC.HLfit
compute model selection/information criteria such as AIC. See the Details for more information about these criteria.
dev_resids
returns a vector of deviance residuals.
deviance
returns the sum of these deviance residuals.
fitted
extracts fitted values (see fitted.values
).
fixef
extracts the fixed effects coefficients, $\beta$.
ranef
extracts the predicted random effects, $u$.
vcov
returns the variance-covariance matrix of the fixed-effects coefficients.
Corr
returns a correlation matrix of random effects (with restrictions, see Details).
getDistMat
extracts a distance matrix for a Matérn correlation model.
"logLik"(object,which,...)
"fitted"(object,...)
"fixef"(object,...)
"ranef"(object,...)
"vcov"(object,...)
"deviance"(object,...)
getDistMat(object,scaled=FALSE)
Corr(object,...)
dev_resids(object,...)
get_any_IC(object, ..., verbose=interactive())
"AIC"(object, ..., k, verbose=interactive())
APHLs
list to return. The default depends on the fitting method.In particular, if it was REML or one of its variants, the function returns the log restricted likelihood (exact or approximated).FALSE
, the function ignores the scale parameter $rho$ and returns unscaled distance.AIC
, unused by HLfit
method, but included to conform to the generic.logLik
), vectors (most cases), matrices (for vcov
), matrices or dist objects (for getDistMat
). ranef
returns a vector with attributes, which inherits from class ranef
which has its own (undocumented) print
method.Corr
currently returns the correlation matrix of the random effects which are described as Lv (see HLfit
)get_any_IC
computes, optionally prints, and returns invisibly the following quantities. The Effective degrees of freedom for the random effects (approximately) characterizes the expectation of a goodness of fit statistic discussed by Lee and Nelder (2001), which gave a general formula for it in HGLMs. The conditional AIC (Vaida and Blanchard 2005) is notable in involving the conditional likelihood and the effective degrees of freedom. Lee et al. (2006) and Ha et al (2007) defined a corrected AIC [i.e., AIC(D*) in their eq. 7] that is here interpreted as the conditional AIC. The conditional AIC returned by HLfit
includes both this effective df, the df for estimated fixed effects, and the df for estimated parameters of the variance of random effects.Also returned are the marginal AIC (Akaike's classical AIC), and a focussed AIC for dispersion parameters (dispersion AIC) discussed by Ha et al (2007; eq.10). This diversity of criteria should encourage users to think twice before applying model selection automatically, which is no better although more fashionable than misuses of simple null hypothesis testing. Also, alternative procedures for model choice can be considered (e.g. Cox and Donnelly, 2011, p. 130-131).data(wafers)
m1 <- HLfit(y ~X1+X2+(1|batch),
resid.model = ~ 1 ,data=wafers,HLmethod="ML")
get_any_IC(m1)
fixef(m1)
vcov(m1)
ranef(m1)
Run the code above in your browser using DataCamp Workspace