lme4::glmer but with multimembership random effects
Usage
glmer(
formula,
data = NULL,
family,
control = lme4::glmerControl(),
start = NULL,
verbose = 0L,
nAGQ = 1L,
weights = NULL,
na.action = na.omit,
offset = NULL,
contrasts = NULL,
devFunOnly = FALSE,
memberships = NULL
)
Arguments
- formula
a two-sided linear formula object describing both the fixed-effects and random-effects part of the model, with the response on the left of a
~
operator and the terms, separated by+
operators, on the right. Random-effects terms are distinguished by vertical bars ("|"
) separating expressions for design matrices from grouping factors.- data
an optional data frame containing the variables named in
formula
. By default the variables are taken from the environment from whichlmer
is called. Whiledata
is optional, the package authors strongly recommend its use, especially when later applying methods such asupdate
anddrop1
to the fitted model (such methods are not guaranteed to work properly ifdata
is omitted). Ifdata
is omitted, variables will be taken from the environment offormula
(if specified as a formula) or from the parent frame (if specified as a character vector).- family
- control
a list (of correct class, resulting from
lmerControl()
orglmerControl()
respectively) containing control parameters, including the nonlinear optimizer to be used and parameters to be passed through to the nonlinear optimizer, see the*lmerControl
documentation for details.- start
a named list of starting values for the parameters in the model, or a numeric vector. A numeric
start
argument will be used as the starting value oftheta
. Ifstart
is a list, thetheta
element (a numeric vector) is used as the starting value for the first optimization step (default=1 for diagonal elements and 0 for off-diagonal elements of the lower Cholesky factor); the fitted value oftheta
from the first step, plusstart[["fixef"]]
, are used as starting values for the second optimization step. Ifstart
has bothfixef
andtheta
elements, the first optimization step is skipped. For more details or finer control of optimization, seemodular
.- verbose
integer scalar. If
> 0
verbose output is generated during the optimization of the parameter estimates. If> 1
verbose output is generated during the individual penalized iteratively reweighted least squares (PIRLS) steps.- nAGQ
integer scalar - the number of points per axis for evaluating the adaptive Gauss-Hermite approximation to the log-likelihood. Defaults to 1, corresponding to the Laplace approximation. Values greater than 1 produce greater accuracy in the evaluation of the log-likelihood at the expense of speed. A value of zero uses a faster but less exact form of parameter estimation for GLMMs by optimizing the random effects and the fixed-effects coefficients in the penalized iteratively reweighted least squares step. (See Details.)
- weights
an optional vector of ‘prior weights’ to be used in the fitting process. Should be
NULL
or a numeric vector.- na.action
a function that indicates what should happen when the data contain
NA
s. The default action (na.omit
, inherited from the ‘factory fresh’ value ofgetOption("na.action")
) strips any observations with any missing values in any variables.- offset
this can be used to specify an a priori known component to be included in the linear predictor during fitting. This should be
NULL
or a numeric vector of length equal to the number of cases. One or moreoffset
terms can be included in the formula instead or as well, and if more than one is specified their sum is used. Seemodel.offset
.- contrasts
an optional list. See the
contrasts.arg
ofmodel.matrix.default
.- devFunOnly
logical - return only the deviance evaluation function. Note that because the deviance function operates on variables stored in its environment, it may not return exactly the same values on subsequent calls (but the results should always be within machine tolerance).
- memberships
named list of weight matrices that will replace any (dummy) random effects with matching names
Examples
df <- data.frame(
x = runif(60, 0, 1),
y = rbinom(60, 1, 0.6),
memberships = rep(c("a,b,c", "a,c", "a", "b", "b,a", "b,c,a"), 10)
)
weights <- weights_from_vector(df$memberships)
# note that the grouping variable name is arbitrary -- it just has
# to match the name in the list and doesn't need to correspond to a column
# name in the data
glmer(y ~ x + (1 | members),
data = df,
family = binomial,
memberships = list(members = weights)
)
#> Generalized linear mixed model fit by maximum likelihood (Laplace
#> Approximation) [glmerModMultiMember]
#> Family: binomial ( logit )
#> Formula: y ~ x + (1 | members)
#> Data: df
#> AIC BIC logLik deviance df.resid
#> 83.4162 89.6992 -38.7081 77.4162 57
#> Random effects:
#> Groups Name Std.Dev.
#> members (Intercept) 0
#> Number of obs: 60, groups: members, 3
#> Fixed Effects:
#> (Intercept) x
#> 0.3690 0.4972