dredge: Automatized model selection

Description

Automatically generate models with combinations of the terms in the global model, with optional rules for inclusion.

Usage

dredge(global.model, beta = FALSE, evaluate = TRUE, rank = "AICc",
    fixed = NULL, m.max = NA, m.min = 0, subset, marg.ex = NULL,
    trace = FALSE, varying = NULL, ...)
## S3 method for class 'model.selection':
print(x, abbrev.names = TRUE, ...)

Arguments

global.model

a fitted global model object. See Details for a list of supported types.

beta

logical, should standardized coefficients be returned?

evaluate

whether to evaluate and rank the models. If FALSE, a list of model calls is returned.

rank

optional custom rank function (information criterion) to be used instead AICc, e.g. QAIC or BIC. See Details.

fixed

optional, either a single sided formula or a character vector giving names of terms to be included in all models.

m.max, m.min

optional, maximum and minimum number of terms in a single model (excluding the intercept), m.max defaults to the number of terms in global.model.

subset

logical expression indicating models to keep in the resulting set. See Details.

marg.ex

a character vector specifying names of variables for which NOT to check for marginality restrictions when generating model formulas. If this argument is set to TRUE, all combinations of terms are used (i.e. no checking).

trace

if TRUE, all calls to the fitting function (i.e. updated global.model calls) are printed.

varying

optionally, a named list describing the additional arguments to vary between the generated models. Names are the names of the arguments, and each item provides a list of choices. Complex items in the choice list (such as family objects)

a model.selection object, returned by dredge.

abbrev.names

should variable names be abbreviated when printing? (useful with many variables).

...

optional arguments for the rank function. Any can be an expression (of mode call), in which case any x within it will be substituted with a current model.

Value

dredge returns an object of class model.selection, being a data.frame with models' coefficients (or TRUE/FALSE for factors), k, deviance/RSS, R-squared, AIC, AICc, delta and Akaike weight. This depends on a type of model. Models are ordered according to the used information criterion (lowest on top), specified by rank.
The attribute "calls" is a list containing the model calls used (arranged in the same order as the models).

encoding

utf-8

Details

dregde currently is known to work with lm, glm, rlm, polr, multinom, gam, gls, lme, lmer, coxph, glmmML, sarlm, spautolm, gamm and gamm4 (the last two should be fitted via the wrapper MuMIn::gamm).

Models are run one by one by repeated evaluation of modified calls to global.model (in a similar fashion to that of update. This method, while robust in that it can be applied to a variety of different model ofjects is not very efficient, and may be time-intensive.

Note that the number of combinations grows exponentially with number of predictor variables (latex{$2^{N}$}{2^N}). Because there is potentially a large number of models to evaluate, to avoid memory overflow the fitted model objects are not stored. To get (a subset of) the models, use get.models on the object returned by dredge.

Handling interactions, dredge respects marginality constraints, so all possible combinations do not include models containing interactions without their respective main effects. This behaviour can be altered by marg.ex argument. It can be used to allow for simple nested designs. For example, with global model of form a / (x + z), use marg.ex = "a" and fixed = "a".

rank is found by a call to match.fun and may be specified as a function or a symbol (e.g. a back-quoted name) or a character string specifying a function to be searched for from the environment of the call to dredge. Function rank must be able to accept model as a first argument and must always return a scalar. Typical choice for rank would be "AIC", "QAIC" or "BIC" (stats or nlme).

The argument subset acts in a similar fashion to that in the function subset for data.frames: the model terms can be referred to by name as variables in the expression, with the difference that they are always logical (i.e. TRUE if a term exists in the model). The expression can contain any of the global.model terms (use getAllTerms(global.model) to list them). It can have a form of an unevaluated call, expression object, or a one sided formula. See Examples. Compound model terms (such as as-is expressions within I() or the smooths in gam) should be treated as non-syntactic names and enclosed in back-ticks (see Quotes). Mind the spacing, names must match exactly the term names in model's formula. To simply keep certain variables in all models, use of fixed is preferred.

Use of na.action = na.omit (R's default) in global.model should be avoided, as it results with sub-models fitted to different data sets, if there are missing values. In versions >= 0.13.17 a warning is given in such a case.

Examples

Run this code

# Example from Burnham and Anderson (2002), page 100:
data(Cement)
fm1 <- lm(y ~ ., data = Cement)
dd <- dredge(fm1)
subset(dd, delta < 4)

# Visualize the model selection table:
if(require(graphics))
plot(dd)


# Model average models with delta AICc < 4
model.avg(get.models(dd, subset = delta < 4))

#or as a 95\% confidence set:
confset.95p <- get.models(dd, cumsum(weight) <= .95)

model.avg(confset.95p) # get averaged coefficients

#'Best' model
summary(confset.95p[[1]])

# Examples of using 'subset':
# exclude models containing both X1 and X2
dredge(fm1, subset = !(X1 & X2))
# keep only models containing X3
dredge(fm1, subset = ~ X3) # subset as a formula
dredge(fm1, subset = expression(X3)) # subset as expression object
# the same, but more effective:
dredge(fm1, fixed = "X3")

#Reduce the number of generated models, by including only those with
# up to 2 terms (and intercept)
dredge(fm1, m.max = 2)

Run the code above in your browser using DataLab