We will see how to perform exponential regressions and how to plot these curved regression lines in base R and ggplot2, using the lines and geom_line functions, respectively. Please read my article about adding curved lines in base R and ggplot2 if you are interested in the different plotting options.
Load the dataset
data("iris")Variables assignment
dataset = iris
x_column = "Sepal.Length"
y_column = "Petal.Length"Exponential regression
lm_results = lm(log(dataset[, y_column]) ~ dataset[, x_column])Extract the exponential regression coefficients
intercept = coef(lm_results)[[1]]
slope = coef(lm_results)[[2]]Compute the fitted values
dataset = dataset[order(dataset[, x_column]),]
dataset[, "exp"] = exp(slope * dataset[, x_column] + intercept)Line color
acol = palette()[4]Add an exponential regression line in base R
plot(dataset[, x_column], dataset[, y_column], pch = 18,
xlab = x_column, ylab = y_column)
lines(dataset[, x_column], dataset[, "exp"], col = acol, lwd = 3)
Add a exponential regression line in ggplot2
library(ggplot2)
ggplot(dataset, aes_string(x = x_column, y = y_column)) +
geom_point(shape = 18)+
geom_line(data = data.frame(x = dataset[, x_column], y = dataset[, "exp"]),
aes(x = x, y = y), col = acol, lwd = 1)
Conclusion
In conclusion, it is possible to perform an exponential regression using the lm function and to plot the resulting line using base R graphics as well as the ggplot2 package.
This was extremely helpful!!!!! I have been dealing with it for days!! Thank you so much!!!
I’m glad it helped you! Thank you for your feedback, this is the first comment on my blog and it means a lot to me!