multiplot: Plot multiple coefplots

Description

Plot the coefficients from multiple models

Usage

multiplot(
  ...,
  title = "Coefficient Plot",
  xlab = "Value",
  ylab = "Coefficient",
  innerCI = 1,
  outerCI = 2,
  lwdInner = 1,
  lwdOuter = (Sys.info()["sysname"] != "Windows") * 0.5,
  pointSize = 3,
  dodgeHeight = 1,
  color = "blue",
  shape = 16,
  linetype = 1,
  cex = 0.8,
  textAngle = 0,
  numberAngle = 90,
  zeroColor = "grey",
  zeroLWD = 1,
  zeroType = 2,
  single = TRUE,
  scales = "fixed",
  ncol = length(unique(modelCI$Model)),
  sort = c("natural", "normal", "magnitude", "size", "alphabetical"),
  decreasing = FALSE,
  names = NULL,
  numeric = FALSE,
  fillColor = "grey",
  alpha = 1/2,
  horizontal = FALSE,
  factors = NULL,
  only = NULL,
  shorten = TRUE,
  intercept = TRUE,
  interceptName = "(Intercept)",
  coefficients = NULL,
  predictors = NULL,
  strict = FALSE,
  newNames = NULL,
  plot = TRUE,
  drop = FALSE,
  by = c("Coefficient", "Model"),
  plot.shapes = FALSE,
  plot.linetypes = FALSE,
  legend.position = c("bottom", "right", "left", "top", "none"),
  secret.weapon = FALSE,
  legend.reverse = FALSE,
  trans = identity
)

Value

A ggplot object

Arguments

...: Models to be plotted
title: The name of the plot, if NULL then no name is given
xlab: The x label
ylab: The y label
innerCI: How wide the inner confidence interval should be, normally 1 standard deviation. If 0, then there will be no inner confidence interval.
outerCI: How wide the outer confidence interval should be, normally 2 standard deviations. If 0, then there will be no outer confidence interval.
lwdInner: The thickness of the inner confidence interval
lwdOuter: The thickness of the outer confidence interval
pointSize: Size of coefficient point
dodgeHeight: Amount of vertical dodging
color: The color of the points and lines
shape: The shape of the points
linetype: The type of line drawn for the standard errors
cex: The text size multiplier, currently not used
textAngle: The angle for the coefficient labels, 0 is horizontal
numberAngle: The angle for the value labels, 0 is horizontal
zeroColor: The color of the line indicating 0
zeroLWD: The thickness of the 0 line
zeroType: The type of 0 line, 0 will mean no line
single: logical; If TRUE there will be one plot with the points and bars stacked, otherwise the models will be displayed in separate facets
scales: The way the axes should be treated in a faceted plot. Can be c("fixed", "free", "free_x", "free_y")
ncol: The number of columns that the models should be plotted in
sort: Determines the sort order of the coefficients. Possible values are c("natural", "magnitude", "alphabetical")
decreasing: logical; Whether the coefficients should be ascending or descending
names: Names for models, if NULL then they will be named after their inputs
numeric: logical; If true and factors has exactly one value, then it is displayed in a horizontal graph with continuous confidence bounds.
fillColor: The color of the confidence bounds for a numeric factor
alpha: The transparency level of the numeric factor's confidence bound
horizontal: logical; If the plot should be displayed horizontally
factors: Vector of factor variables that will be the only ones shown
only: logical; If factors has a value this determines how interactions are treated. True means just that variable will be shown and not its interactions. False means interactions will be included.
shorten: logical or character; If FALSE then coefficients for factor levels will include their variable name. If TRUE coefficients for factor levels will be stripped of their variable names. If a character vector of variables only coefficients for factor levels associated with those variables will the variable names stripped.
intercept: logical; Whether the Intercept coefficient should be plotted
interceptName: Specifies name of intercept it case it is not the default of "(Intercept").
coefficients: A character vector specifying which factor coefficients to keep. It will keep all levels and any interactions, even if those are not listed.
predictors: A character vector specifying which coefficients to keep. Each individual coefficient can be specified. Use predictors to specify entire factors
strict: If TRUE then predictors will only be matched to its own coefficients, not its interactions
newNames: Named character vector of new names for coefficients
plot: logical; If the plot should be drawn, if false then a data.frame of the values will be returned
drop: logical; if TRUE then models without valid coefficients to show will not be plotted
by: If "Coefficient" then a normal multiplot is plotted, if "Model" then the coefficients are plotted along the axis with one for each model. If plotting by model only one coefficient at a time can be selected. This is called the secret weapon by Andy Gelman.
plot.shapes: If TRUE points will have different shapes for different models
plot.linetypes: If TRUE lines will have different shapes for different models
legend.position: position of legend, one of "left", "right", "bottom", "top", "none"
secret.weapon: If this is TRUE and exactly one coefficient is listed in coefficients then Andy Gelman's secret weapon is plotted.
legend.reverse: Setting to reverse the legend in a multiplot so that it matches the order they are drawn in the plot
trans: A transformation function to apply to the values and confidence intervals. identity by default. Use invlogit for binary regression.

Details

Plots a graph similar to coefplot but for multiple plots at once.

For now, if names is provided the plots will appear in alphabetical order of the names. This will be adjusted in future iterations. When setting by to "Model" and specifying exactly one variable in variables that one coefficient will be plotted repeatedly with the axis labeled by model. This is Andy Gelman's secret weapon.

Examples

Run this code


data(diamonds)
model1 <- lm(price ~ carat + cut, data=diamonds)
model2 <- lm(price ~ carat + cut + color, data=diamonds)
model3 <- lm(price ~ carat + color, data=diamonds)
multiplot(model1, model2, model3)
multiplot(model1, model2, model3, single=FALSE)
multiplot(model1, model2, model3, plot=FALSE)
require(reshape2)
data(tips, package="reshape2")
mod1 <- lm(tip ~ total_bill + sex, data=tips)
mod2 <- lm(tip ~ total_bill * sex, data=tips)
mod3 <- lm(tip ~ total_bill * sex * day, data=tips)
mod7 <- lm(tip ~ total_bill + day + time, data=tips)
multiplot(mod1, mod2, mod3, mod7, single=FALSE, scales="free_x")
multiplot(mod1, mod2, mod3, mod7, single=FALSE, scales="free_x")
multiplot(mod1, mod2, mod3, mod7, single=FALSE, scales="free_x", plot.shapes=TRUE)
multiplot(mod1, mod2, mod3, mod7, single=TRUE, scales="free_x", 
plot.shapes=TRUE, plot.linetypes=TRUE)
multiplot(mod1, mod2, mod3, mod7, single=TRUE, scales="free_x", 
plot.shapes=FALSE, plot.linetypes=TRUE, legend.position="bottom")
# the secret weapon
multiplot(mod1, mod2, mod3, mod7, coefficients="total_bill", secret.weapon=TRUE)
# horizontal secret weapon
multiplot(mod1, mod2, mod3, mod7, coefficients="total_bill", by="Model", horizontal=FALSE)