arm (version 1.14-4)

coefplot: Generic Function for Making Coefficient Plot

Description

Functions that plot the coefficients plus and minus 1 and 2 sd from a lm, glm, bugs, and polr fits.

Usage

coefplot(object,...)
# S3 method for default
coefplot(coefs, sds, CI=2, 
                lower.conf.bounds, upper.conf.bounds,
                varnames=NULL, vertical=TRUE, 
                v.axis=TRUE, h.axis=TRUE,
                cex.var=0.8, cex.pts=0.9, 
                col.pts=1, pch.pts=20, var.las=2,
                main=NULL, xlab=NULL, ylab=NULL, mar=c(1,3,5.1,2),
                plot=TRUE, add=FALSE, offset=.1, ...)
# S4 method for bugs
coefplot(object, var.idx=NULL, varnames=NULL, 
            CI=1, vertical=TRUE,
            v.axis=TRUE, h.axis=TRUE, 
            cex.var=0.8, cex.pts=0.9, 
            col.pts=1, pch.pts=20, var.las=2, 
            main=NULL, xlab=NULL, ylab=NULL, 
            plot=TRUE, add=FALSE, offset=.1,
            mar=c(1,3,5.1,2), ...)
# S4 method for numeric
coefplot(object, ...)
# S4 method for lm
coefplot(object, varnames=NULL, intercept=FALSE, ...)
# S4 method for glm
coefplot(object, varnames=NULL, intercept=FALSE, ...)
# S4 method for polr
coefplot(object, varnames=NULL, ...)

Value

Plot of the coefficients from a bugs, lm or glm fit. You can add the intercept, the variable names and the display the result of the fitted model.

Arguments

object

fitted objects-lm, glm, bugs and polr, or a vector of coefficients.

...

further arguments passed to or from other methods.

coefs

a vector of coefficients.

sds

a vector of sds of coefficients.

CI

confidence interval, default is 2, which will plot plus and minus 2 sds or 95% CI. If CI=1, plot plus and minus 1 sds or 50% CI instead.

lower.conf.bounds

lower bounds of confidence intervals.

upper.conf.bounds

upper bounds of confidence intervals.

varnames

a vector of variable names, default is NULL, which will use the names of variables; if specified, the length of varnames must be equal to the length of predictors, including the intercept.

vertical

orientation of the plot, default is TRUE which will plot variable names in the 2nd axis. If FALSE, plot variable names in the first axis instead.

v.axis

default is TRUE, which shows the bottom axis--axis(1).

h.axis

default is TRUE, which shows the left axis--axis(2).

cex.var

The fontsize of the varible names, default=0.8.

cex.pts

The size of data points, default=0.9.

col.pts

color of points and segments, default is black.

pch.pts

symbol of points, default is solid dot.

var.las

the orientation of variable names against the axis, default is 2. see the usage of las in par.

main

The main title (on top) using font and size (character expansion) par("font.main") and color par("col.main").

xlab

X axis label using font and character expansion par("font.lab") and color par("col.lab").

ylab

Y axis label, same font attributes as xlab.

mar

A numerical vector of the form c(bottom, left, top, right) which gives the number of lines of margin to be specified on the four sides of the plot. The default is c(1,3,5.1,2).

plot

default is TRUE, plot the estimates.

add

if add=TRUE, plot over the existing plot. default is FALSE.

offset

add extra spaces to separate from the existing dots. default is 0.1.

var.idx

the index of the variables of a bugs object, default is NULL which will plot all the variables.

intercept

If TRUE will plot intercept, default=FALSE to get better presentation.

Author

Yu-Sung Su

Details

This function plots coefficients from bugs, lm, glm and polr with 1 sd and 2 sd interval bars.

References

Andrew Gelman and Jennifer Hill, Data Analysis Using Regression and Multilevel/Hierarchical Models, Cambridge University Press, 2006.

See Also

display, par, lm, glm, bayesglm, plot

Examples

old.par <- par(no.readonly = TRUE)

 y1 <- rnorm(1000,50,23)
 y2 <- rbinom(1000,1,prob=0.72)
 x1 <- rnorm(1000,50,2) 
 x2 <- rbinom(1000,1,prob=0.63) 
 x3 <- rpois(1000, 2) 
 x4 <- runif(1000,40,100) 
 x5 <- rbeta(1000,2,2) 
 
 longnames <- c("a long name01","a long name02","a long name03",
                "a long name04","a long name05")

 fit1 <- lm(y1 ~ x1 + x2 + x3 + x4 + x5)
 fit2 <- glm(y2 ~ x1 + x2 + x3 + x4 + x5, 
            family=binomial(link="logit"))
 op <- par()
 # plot 1
 par (mfrow=c(2,2))
 coefplot(fit1)
 coefplot(fit2, col.pts="blue")
 
 # plot 2
 longnames <- c("(Intercept)", longnames) 
 coefplot(fit1, longnames, intercept=TRUE, CI=1)
 
 # plot 3
 coefplot(fit2, vertical=FALSE, var.las=1, frame.plot=TRUE)
 
 # plot 4: comparison to show bayesglm works better than glm
 n <- 100
 x1 <- rnorm (n)
 x2 <- rbinom (n, 1, .5)
 b0 <- 1
 b1 <- 1.5
 b2 <- 2
 y <- rbinom (n, 1, invlogit(b0+b1*x1+b2*x2))
 y <- ifelse (x2==1, 1, y)
 x1 <- rescale(x1)
 x2 <- rescale(x2, "center")
 
 M1 <- glm (y ~ x1 + x2, family=binomial(link="logit"))
       display (M1)
 M2 <- bayesglm (y ~ x1 + x2, family=binomial(link="logit"))
       display (M2)

#=================== 
#    stacked plot
#===================
  coefplot(M2, xlim=c(-1,5), intercept=TRUE)
  coefplot(M1, add=TRUE, col.pts="red")
  
#==================== 
# arrayed plot       
#====================
  par(mfrow=c(1,2))
  x.scale <- c(0, 7.5) # fix x.scale for comparison
  coefplot(M1, xlim=x.scale, main="glm", intercept=TRUE)
  coefplot(M2, xlim=x.scale, main="bayesglm", intercept=TRUE)

# plot 5: the ordered logit model from polr
 M3 <- polr(Sat ~ Infl + Type + Cont, weights = Freq, data = housing)
 coefplot(M3, main="polr")
   
 M4 <- bayespolr(Sat ~ Infl + Type + Cont, weights = Freq, data = housing)
 coefplot(M4, main="bayespolr", add=TRUE, col.pts="red")

## plot 6: plot bugs & lmer
# par <- op
# M5 <- lmer(Reaction ~ Days + (1|Subject), sleepstudy)
# M5.sim <- mcsamp(M5)
# coefplot(M5.sim, var.idx=5:22, CI=1, ylim=c(18,1), main="lmer model")


# plot 7: plot coefficients & sds vectors
 coef.vect <- c(0.2, 1.4, 2.3, 0.5)
 sd.vect <- c(0.12, 0.24, 0.23, 0.15)
 longnames <- c("var1", "var2", "var3", "var4")
 coefplot (coef.vect, sd.vect, varnames=longnames, main="Regression Estimates")
 coefplot (coef.vect, sd.vect, varnames=longnames, vertical=FALSE, 
    var.las=1, main="Regression Estimates")
    
par(old.par)