I am not really confident in interpreting the ANOVA table of a GAM model. I understand how it can be used to compare models (see for instance this question), but I am interested in interpreting it for a single model.

For concreteness:

library( mgcv )
set.seed( 1 )
RawData <- data.frame( y = rbinom( 1000, 1, 0.5 ), x1 = rnorm( 1000 ), x2 = as.factor( rbinom( 1000, 1, 0.5 ) ), x3 = rnorm( 1000 ), x4 = as.factor( rbinom( 1000, 1, 0.5 ) ) )
fit <- gam( y ~ s( x1 ) + x2 + s( x3, by = x2 ) + x4, data = RawData, family = nb( link = log ) )
anova( fit )

Family: Negative Binomial(251657.167) 
Link function: log

y ~ s(x1) + x2 + s(x3, by = x2) + x4

Parametric Terms:
   df Chi.sq p-value
x2  1  1.775   0.183
x4  1  0.796   0.372

Approximate significance of smooth terms:
            edf Ref.df Chi.sq p-value
s(x1)     1.000  1.000  0.047   0.828
s(x3):x20 1.000  1.000  0.078   0.779
s(x3):x21 1.000  1.001  0.188   0.665

In particular, I'd be interested in the following:

  1. Can chi.sq values be given an "explained variance" interpretation (or similar), i.e. can they be used to measure variable importance, just like for a usual linear model?
  2. Can the chi.sq values of the smooth and parametric terms handled similarly?
  3. What to do with interactions? (As x2 and x3 in the example: x3 appears on two lines, x2 appears in those, and as a parametric term in addition.)

1 Answer 1


It's probably best to take a look at the mgcv help file ?anova.gam in R, but in answer to the specific questions:

  1. The parametric chi.sq test statistics are just like their linear model equivalents, but the test statistic used for the smooths is different, and doesn't have an explained variance interpretation. I would not try to use them directly to measure variable importance. For details see http://opus.bath.ac.uk/32382/1/spv3.pdf.

  2. No, as explained above.

  3. I would fit the model with and without the interaction and compare (but probably by AIC).

Simon Wood

  • 1
    $\begingroup$ Thank you very much! In that case, may I ask you what do you suggest to measure the relative importance of all variables (i.e. smooth terms included) in a GAM model...? $\endgroup$ Nov 10, 2017 at 0:23
  • $\begingroup$ I have added this as a separate question ( stats.stackexchange.com/questions/313957/… ), after all it is indeed a different story, so it is better not to mix the two. $\endgroup$ Nov 15, 2017 at 20:18

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.