hglm (version 2.2-1)

plot.hglm: Plot Hierarchical Generalized Linear Model Objects

Description

Plots residuals for the mean and dispersion models, individual deviances and hatvalues for hglm objects

Usage

# S3 method for hglm
plot(x, pch = "+", pcol = 'slateblue', lcol = 2, 
                    device = NULL, name = NULL, ...)

Arguments

x

the hglm object to be plotted

pch

symbol used in the plots

pcol

color of points

lcol

color of lines

device

if NULL, plot on screen devices, if 'pdf', plot to PDF files in the current working directory.

name

a string gives the main name of the PDF file when device = 'pdf'.

…

graphical parameters

Details

A S3 generic plot method for hglm objects. It produces a set of diagnostic plots for a hierarchical model.

Examples

# NOT RUN {
# --------------------- #
# semiconductor example #
# --------------------- #

data(semiconductor)

h.gamma.normal <- hglm(fixed = y ~ x1 + x3 + x5 + x6,
                       random = ~ 1|Device,
                       family = Gamma(link = log),
                       disp = ~ x2 + x3, data = semiconductor)
summary(h.gamma.normal)
plot(h.gamma.normal, cex = .6, pch = 1,
     cex.axis = 1/.6, cex.lab = 1/.6,
     cex.main = 1/.6, mar = c(3, 4.5, 0, 1.5))

# ------------------- #
# redo it using hglm2 #
# ------------------- #

m1 <- hglm2(y ~ x1 + x3 + x5 + x6 + (1|Device),
            family = Gamma(link = log),
            disp = ~ x2 + x3, data = semiconductor)
summary(m1)
plot(m1, cex = .6, pch = 1,
     cex.axis = 1/.6, cex.lab = 1/.6,
     cex.main = 1/.6, mar = c(3, 4.5, 0, 1.5))

# --------------------------------------------- #  
# simulated example with 2 random effects terms #
# --------------------------------------------- #  
# }
# NOT RUN {
set.seed(911)
x1 <- rnorm(100)
x2 <- rnorm(100)
x3 <- rnorm(100)
z1 <- factor(rep(LETTERS[1:10], rep(10, 10)))
z2 <- factor(rep(letters[1:5], rep(20, 5)))
Z1 <- model.matrix(~ 0 + z1)
Z2 <- model.matrix(~ 0 + z2)
u1 <- rnorm(10, 0, sqrt(2))
u2 <- rnorm(5, 0, sqrt(3))
y <- 1 + 2*x1 + 3*x2 + Z1%*%u1 + Z2%*%u2 + rnorm(100, 0, sqrt(exp(x3)))
dd <- data.frame(x1 = x1, x2 = x2, x3 = x3, z1 = z1, z2 = z2, y = y)

(m2.1 <- hglm(X = cbind(rep(1, 100), x1, x2), y = y, Z = cbind(Z1, Z2), 
              RandC = c(10, 5)))
summary(m2.1)
plot(m2.1)

(m2.2 <- hglm2(y ~ x1 + x2 + (1|z1) + (1|z2), data = dd, vcovmat = TRUE))
image(m2.2$vcov)
summary(m2.2)
plot(m2.2)

m3 <- hglm2(y ~ x1 + x2 + (1|z1) + (1|z2), disp = ~ x3, data = dd)
print (m3)
summary(m3)
plot(m3)
# }