# scatter plot
# create simulated data, no population mean difference
# X has two values only, Y is numeric
# put into a data frame, required for formula version
n <- 12
f <- sample(c("Group1","Group2"), size=n, replace=TRUE)
x <- round(rnorm(n=n, mean=50, sd=10), 2)
y <- round(rnorm(n=n, mean=50, sd=10), 2)
z <- round(rnorm(n=n, mean=50, sd=10), 2)
mydata <- data.frame(f,x,y,z)
rm(f); rm(x); rm(y); rm(z)
# default scatterplot, x is not sorted so type is set to "p"
Plot(x, y)
# short name
plt(x,y)
# compare to standard R plot, which requires the mydata$ notation
plot(mydata$x, mydata$y)
# scatterplot, with ellipse and extended axes to accommodate the ellipse
Plot(x, y, ellipse=TRUE, xlim=c(20,80), ylim=c(20,80))
# scatterplot, with loess line
Plot(x, y, fit.line="loess")
# increase span (smoothing) from default of .75
Plot(x, y, fit.line="loess", span=1)
# custom scatter plot
Plot(x, y, col.pts="darkred", col.fill="plum")
# scatter plot with a gray scale color theme
Plot(x, y, colors="gray")
# scatterplot matrix and correlation matrix
# first remove the categorical variable f from mydata
mydata <- subset(mydata, select=c(x:z))
# now analyze remaining variables x, y and z
Plot(mydata)
# bubble plot of simulated Likert data, 1 to 7 scale
# size of each plotted point (bubble) depends on its joint frequency
# triggered by default when < 10 unique values for each variable
x1 <- sample(1:7, size=100, replace=TRUE)
x2 <- sample(1:7, size=100, replace=TRUE)
Plot(x1,x2)
# compare to usual scatterplot of Likert data, transparency helps
Plot(x1,x2, kind="regular")
Plot(x1,x2, kind="regular", cex=3, trans.pts=.7)
# plot Likert data and get sunflower plot with loess line
Plot(x1,x2, kind="sunflower", fit.line="loess")
# scatterplot of continuous Y against categorical X, a factor
Pain <- sample(c("None", "Some", "Much", "Massive"), size=25, replace=TRUE)
Pain <- factor(Pain, levels=c("None", "Some", "Much", "Massive"), ordered=TRUE)
Cost <- round(rnorm(25,1000,100),2)
Plot(Pain, Cost)
# for this purpose, improved version of standard R stripchart
stripchart(Cost ~ Pain, vertical=TRUE)
# line chart, that is, function curve
x <- seq(10,500,by=1)
y <- 18/sqrt(x)
# x is sorted with equal intervals so type set to "l" for line
Plot(x, y)
# custom function plot
Plot(x, y, ylab="My Y", xlab="My X", col.line="blue",
col.bg="snow", col.area="lightsteelblue", col.grid="lightsalmon")
# Default dot plot
Plot(y)
# Dot plot with custom colors for outliers
Plot(y, pt.reg=23, col.out15="blue", col.out30="red")
# modern art
n <- sample(2:30, size=1)
x <- rnorm(n)
y <- rnorm(n)
clr <- colors()
color1 <- clr[sample(1:length(clr), size=1)]
color2 <- clr[sample(1:length(clr), size=1)]
Plot(x, y, type="l", lty="dashed", lwd=3, col.area=color1,
col.line=color2, xy.ticks=FALSE, main="Modern Art",
cex.main=2, col.main="lightsteelblue", kind="regular",
ncut=0)
# --------------------------------------------
# plots for data frames and multiple variables
# --------------------------------------------
# create data frame, mydata, to mimic reading data with rad function
# mydata contains both numeric and non-numeric data
mydata <- data.frame(rnorm(100), rnorm(100), rnorm(100), rep(c("A","B"),50))
names(mydata) <- c("X","Y","Z","C")
# although data not attached, access each variable directly by its name
Plot(X)
Plot(X,Y)
# variable of interest is in a data frame which is not the default mydata
# access the breaks and wool variables in the R provided warpbreaks data set
# wool is categorical with two levels, breaks is numeric
# although data not attached, access the variable directly by its name
data(warpbreaks)
Plot(wool, breaks, dframe=warpbreaks)Run the code above in your browser using DataLab