r - lme4 random effect structure with dredge -

i have constructed lme4 model model selection in dredge having trouble aligning random effects relevant fixed effects.the structure of full model follows.

fullmodel<-glmer(y ~x1 + x2 + (0+x1|year) + (0+x1|country) + (0+x2|year) + (0+x2|country) + (1 | year) +(1|country), family=binomial('logit'),data = alldata) 

in model structure, model selection in dredge produces 3 combinations of fixed effects, i.e. x1, x2, , x1+x2, random effect structure remains same in full model, such when fixed effect x1, random effect include (0+x2|year) + (0+x2|country). example model x1 fixed effect, still have x2 within random effects structure follows.

y ~x1 + (0+x1|year) + (0+x1|country) + (0+x2|year) +(0+x2|country) + (1 | year) +(1|country), family=binomial('logit') 

is there way configure dredge not select random effects have other fixed effects specified in them? have x1….x50.

you cannot out-of-box dredge omits (x|g) expressions, can make "wrapper" around (g)lmer replaces "|" terms in formula else (e.g. re(x,g)), dredge thinks these fixed effects. example:

glmerwrap <- function(formula) {      cl <- origcall <- match.call()     cl[[1l]] <- as.name("glmer") # replace 'lmerwrap' 'glmer'     # replace "re" "|" in formula:     f <- as.formula(do.call("substitute", list(formula, list(re = as.name("|")))))     environment(f) <- environment(formula)     cl$formula <- f     x <- eval.parent(cl) # evaluate modified call     # store original call , formula in result:     x@call  <- origcall     attr(x@frame, "formula") <- formula     x } formals(glmerwrap) <- formals(lme4::glmer) 

following example(glmer):

# note use of re(x,group) instead of (x|group) (fm <- glmerwrap(cbind(incidence, size - incidence) ~ period +     re(1, herd) +  re(1, obs), family = binomial, data = cbpp)) 

now,

dredge(fm) 

manipulates both fixed , random effects.