1.Import the library
library(ggplot2)
Two variables: Continuous X, Continuous Y
We’ll use the mtcars data set. The variable cyl is used as grouping
variable.
2. Import data set
data(mtcars)
mtcars$cyl <- as.factor(mtcars$cyl)
head(mtcars[, c("wt", "mpg", "cyl")])
## wt mpg cyl
## Mazda RX4 2.620 21.0 6
## Mazda RX4 Wag 2.875 21.0 6
## Datsun 710 2.320 22.8 4
## Hornet 4 Drive 3.215 21.4 6
## Hornet Sportabout 3.440 18.7 8
## Valiant 3.460 18.1 6
b <- ggplot(mtcars, aes(x = wt, y = mpg))
Possible layers include:
geom_point() for scatter plot
geom_smooth() for adding smoothed line such as regression line
geom_quantile() for adding quantile lines
geom_rug() for adding a marginal rug
geom_jitter() for avoiding overplotting
geom_text() for adding textual annotations
2.1 geom_point(): Scatter plot
# Basic plot
b + geom_point()
# change the color and the point
# by the levels of cyl variable
b + geom_point(aes(color = cyl, shape = cyl))
# Change color manually
b + geom_point(aes(color = cyl, shape = cyl)) +
scale_color_manual(values = c("#999999", "#E69F00", "#56B4E9"))+
theme_minimal()
2.2 geom_smooth(): Add regression line or smoothed conditional
mean
# To add a regression line on a scatter plot, the function geom_smooth() is used in combination with the argument method = lm. lm stands for linear model.
# Regression line only
b + geom_smooth(method = lm)
## `geom_smooth()` using formula = 'y ~ x'
b + stat_smooth(method = "lm")
## `geom_smooth()` using formula = 'y ~ x'
# Point + regression line
# Remove the confidence interval
b + geom_point() +
geom_smooth(method = lm, se = FALSE)
## `geom_smooth()` using formula = 'y ~ x'
# loess method: local regression fitting
b + geom_point() + geom_smooth()
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'
# Change color and shape by groups (cyl)
b + geom_point(aes(color=cyl, shape=cyl)) +
geom_smooth(aes(color=cyl, shape=cyl),
method=lm, se=FALSE, fullrange=TRUE)
## Warning in geom_smooth(aes(color = cyl, shape = cyl), method = lm, se = FALSE, :
## Ignoring unknown aesthetics: shape
## `geom_smooth()` using formula = 'y ~ x'
2.3 geom_quantile(): Add quantile lines from a quantile
regression
ggplot(mpg, aes(cty, hwy)) +
geom_point() + geom_quantile() +
theme_minimal()
## Smoothing formula not specified. Using: y ~ x
ggplot(mpg, aes(cty, hwy)) +
geom_point() + stat_quantile(quantiles = c(0.25, 0.5, 0.75)) # An alternative to geom_quantile() is the function stat_quantile()
## Smoothing formula not specified. Using: y ~ x
2.4 geom_rug(): Add marginal rug to scatter plots
## Add marginal rugs using faithful data
ggplot(faithful, aes(x=eruptions, y=waiting)) + geom_point() + geom_rug()
2.5 geom_jitter(): Jitter points to reduce overplotting
p <- ggplot(mpg, aes(displ, hwy))
# Default scatter plot
p + geom_point()
# Use jitter to reduce overplotting
p + geom_jitter(position = position_jitter(width = 0.5, height = 0.5))
2.6 geom_text(): Textual annotations
b + geom_text(aes(label = rownames(mtcars)))
