Compare two models

From previous exercise you have fitted a model with distance100 and arsenic as explanatory variables. In this exercise you will analyze the impact on the model fit for each of the added variables.

Recall that the models you fitted are as follows and have been preloaded in the workspace:

model_dist = 'switch ~ distance100'
model_dist_ars = 'switch ~ distance100 + arsenic

The dataset wells has also been preloaded in the workspace.

Deze oefening maakt deel uit van de cursus

Generalized Linear Models in Python

Cursus bekijken

Oefeninstructies

Compute the difference in deviance when distance100 is added to the null model.
Compute the difference in deviance when arsenic is added to the model with distance100 variable.

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

# Compute the difference in adding distance100 variable
diff_deviance_distance = ____.____ - ____.____

# Print the computed difference in deviance
print('Adding distance100 to the null model reduces deviance by: ', 
      round(____,3))

# Compute the difference in adding arsenic variable
diff_deviance_arsenic = ____.____ - ____.____

# Print the computed difference in deviance
print('Adding arsenic to the distance model reduced deviance further by: ', 
      round(____,3))

Code bewerken en uitvoeren