binary_calibration_plot: Binary Calibration Plots
In joestoica/STAT-S-432-Package:

Description Usage Arguments Value Examples

View source: R/calib_plot.R

Binary Calibration Plots

1 2	binary_calibration_plot(response, model, breaks = 0:10/10, point.color = "blue", line.color = "red")

`response`	The response variable from the data
`model`	A model object
`breaks`	The number of bins used to create the error bars that will be displayed
`point.color`	The color of the points in the scatterplot
`line.color`	The color of the line y = x

A ggplot2 object

ch <- read.csv("http://www.stat.cmu.edu/~cshalizi/uADA/15/hw/06/ch.csv")
ch.clean <- na.omit(ch)
lr.ch <- glm(start ~ . -country -year +I(exports^2), data=ch, family="binomial") # logistic regression
binary_calibration_plot(y = ch.clean$start, model = lr.ch, breaks = 0:7/10, point.color = "blue", line.color = "red")
library(mgcv)
gam.ch <- gam(start~s(exports)+s(schooling)+s(growth)+s(peace)+s(concentration)+s(lnpop)+s(fractionalization)+dominance, # GAM
binary_calibration_plot(ch.clean$start, gam.ch, breaks=0:9/10, blue, red)