Aan de slagGa gratis aan de slag

Visualizing auto performance uncertainty

Confidence intervals are a very important visual indicator of model fit. Here you'll practice changing the appearance of confidence intervals and transforming the scale of partial effects plots.

Deze oefening maakt deel uit van de cursus

Nonlinear Modeling with Generalized Additive Models (GAMs) in R

Cursus bekijken

Oefeninstructies

  • Plot the model (mod) that uses the mpg data, plotting only the partial effect of weight. Make the confidence interval shaded and "hotpink" in color.
  • Make another plot of the weight partial effect, this time shifting the scale by the value of the intercept using the shift argument, and including the uncertainty of the model intercept using the seWithMean argument.

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

library(mgcv)
# Fit the model
mod <- gam(hw.mpg ~ s(weight) + s(rpm) + s(price) + comp.ratio, 
           data = mpg, method = "REML")

# Plot the weight effect with colored shading
plot(mod, select = 1, ___)

# Make another plot adding the intercept value and uncertainty
plot(mod, select = 1, ___)
Code bewerken en uitvoeren