Help for package geepack

Version:

1.3.12

Title:

Generalized Estimating Equation Package

Maintainer:

Søren Højsgaard <sorenh@math.aau.dk>

Description:

Generalized estimating equations solver for parameters in mean, scale, and correlation structures, through mean link, scale link, and correlation link. Can also handle clustered categorical responses. See e.g. Halekoh and Højsgaard, (2005, <doi:10.18637/jss.v015.i02>), for details.

Encoding:

UTF-8

LazyData:

true

License:

GPL (≥ 3)

NeedsCompilation:

yes

Depends:

R (≥ 3.5.0), methods

Imports:

MASS, broom, magrittr

RoxygenNote:

7.3.2

Packaged:

2024-09-23 07:43:13 UTC; sorenh

Author:

Søren Højsgaard [aut, cre, cph], Ulrich Halekoh [aut, cph], Jun Yan [aut, cph], Claus Thorn Ekstrøm [ctb]

Repository:

CRAN

Date/Publication:

2024-09-23 09:20:08 UTC

Compare Regression Coefficiente between Nested Models

Description

Comparing regression coefficients between models when one model is nested within another for clustered data.

Usage

compCoef(fit0, fit1)

Arguments

fit0

a fitted object of class geese

fit1

another fitted object of class geese

Value

a list of two components:

delta

estimated difference in the coefficients of common covariates from fit0 and fit1

variance

estimated variance matrix of delta

Author(s)

Jun Yan jyan.stat@gmail.com

References

Allison, P. D. (1995). The impact of random predictors on comparisons of coefficients between models: Comment on Clogg, Petkova, and Haritou. American Journal of Sociology, 100(5), 1294–1305.

Clogg, C. C., Petkova, E., and Haritou, A. (1995). Statistical methods for comparing regression coefficients between models. American Journal of Sociology, 100(5), 1261–1293.

Yan, J., Aseltine, R., and Harel, O. (2011). Comparing Regression Coefficients Between Nested Linear Models for Clustered Data with Generalized Estimating Equations. Journal of Educational and Behaviorial Statistics, Forthcoming.

Examples


## generate clustered data
gendat <- function(ncl, clsz) {
## ncl: number of clusters
## clsz: cluster size (all equal)
  id <- rep(1:ncl, each = clsz)
  visit <- rep(1:clsz, ncl)
  n <- ncl * clsz
  x1 <- rbinom(n, 1, 0.5) ## within cluster varying binary covariate
  x2 <- runif(n, 0, 1)   ## within cluster varying continuous covariate
  ## the true correlation coefficient rho for an ar(1)
  ## correlation structure is 2/3
  rho <- 2/3
  rhomat <- rho ^ outer(1:4, 1:4, function(x, y) abs(x - y))
  chol.u <- chol(rhomat)
  noise <- as.vector(sapply(1:ncl, function(x) chol.u %*% rnorm(clsz)))
  y <- 1 + 3 * x1 - 2 * x2 + noise
  dat <- data.frame(y, id, visit, x1, x2)
  dat
}

simdat <- gendat(100, 4)
fit0 <- geese(y ~ x1, id = id, data = simdat, corstr = "un")
fit1 <- geese(y ~ x1 + x2, id = id, data = simdat, corstr = "un")
compCoef(fit0, fit1)

Growth curves of pigs in a 3x3 factorial experiment

Description

The dietox data frame has 861 rows and 7 columns.

Usage

dietox

Format

This data frame contains the following columns:

Weight: Weight in Kg
Feed: Cumulated feed intake in Kg
Time: Time (in weeks) in the experiment
Pig: Factor; id of each pig
Evit: Factor; vitamin E dose; see 'details'.
Cu: Factor, copper dose; see 'details'
Start: Start weight in experiment, i.e. weight at week 1.
Litter: Factor, id of litter of each pig

Details

Data contains weight of slaughter pigs measured weekly for 12 weeks. Data also contains the startweight (i.e. the weight at week 1). The treatments are 3 different levels of Evit = vitamin E (dose: 0, 100, 200 mg dl-alpha-tocopheryl acetat /kg feed) in combination with 3 different levels of Cu=copper (dose: 0, 35, 175 mg/kg feed) in the feed. The cumulated feed intake is also recorded. The pigs are littermates.

Source

Lauridsen, C., Højsgaard, S.,Sørensen, M.T. C. (1999) Influence of Dietary Rapeseed Oli, Vitamin E, and Copper on Performance and Antioxidant and Oxidative Status of Pigs. J. Anim. Sci.77:906-916

Examples


data(dietox)
head(dietox)
## Not run: 
if (require(ggplot2)){
  qplot(Time, Weight, data=dietox, col=Pig) + geom_line() +
        theme(legend.position = "none") + facet_grid(Evit~Cu)
} else {
  coplot(Weight ~ Time | Evit * Cu, data=dietox)
}

## End(Not run)

Construct zcor vector

Description

Construct zcor vector (of fixed correlations) from a fixed working correlation matrix, a specification of clusters and a specifcation of waves.

Usage

fixed2Zcor(cor.fixed, id, waves)

Arguments

cor.fixed

Matrix

id

Clusters

waves

Vector giving the ordering of observations within clusters.

Value

A vector which can be passed as the zcor argument to geeglm.

Author(s)

Søren Højsgaard, sorenh@math.aau.dk

Examples


timeorder <- rep(1:5, 6)
tvar      <- timeorder + rnorm(length(timeorder))
idvar <- rep(1:6, each=5)
uuu   <- rep(rnorm(6), each=5)
yvar  <- 1 + 2*tvar + uuu + rnorm(length(tvar))
simdat <- data.frame(idvar, timeorder, tvar, yvar)
head(simdat,12)

simdatPerm <- simdat[sample(nrow(simdat)),]
simdatPerm <- simdatPerm[order(simdatPerm$idvar),]
head(simdatPerm)

cor.fixed <- matrix(c(1    , 0.5  , 0.25,  0.125, 0.125,
                      0.5  , 1    , 0.25,  0.125, 0.125,
                      0.25 , 0.25 , 1   ,  0.5  , 0.125,
                      0.125, 0.125, 0.5  , 1    , 0.125,
                      0.125, 0.125, 0.125, 0.125, 1     ), nrow=5, ncol=5)
cor.fixed

zcor <- fixed2Zcor(cor.fixed, id=simdatPerm$idvar, waves=simdatPerm$timeorder)
zcor

mod4 <- geeglm(yvar~tvar, id=idvar, data=simdatPerm, corstr="fixed", zcor=zcor)
mod4

Fit Generalized Estimating Equations (GEE)

Description

The geeglm function fits generalized estimating equations using the 'geese.fit' function of the 'geepack' package for doing the actual computations. geeglm has a syntax similar to glm and returns an object similar to a glm object. An important feature of geeglm, is that an anova method exists for these models.