June 2017
Beginner to intermediate
576 pages
15h 22m
English
Next, you can run ggplot to graphically display the errors grouped by outcome. The resulting boxplots show that the three quartiles for diabetes are above the non-diabetic patients. This demonstrates that the model's prediction error runs higher when predicting those patients who actually developed diabetes. This would certainly imply that the model needs to be improved:
library(ggplot2)ggplot(local, aes(factor(outcome),error)) + geom_boxplot()
