1

I've just carried out an ANOVA using the Anova function in the package car, with type III sums of squares and got the following output.

model <- lm(Count ~ Distance*State, data=df)

Anova(model, test="F", type="III")

I'm just wondering what the intercept term in this means?

enter image description here

kjetil b halvorsen
  • 77,844
timeywimey
  • 31
  • The intercept is the fitted value if all predictors are zero. If you have factor variables in your model and are using the default treatment contrasts, the intercept is the mean of the reference group if all continuous predictors are zero. – Roland Feb 14 '23 at 06:15
  • 1
    However, your dependent variable is called "Count", which probably means it's a count variable. You should not use lm then. Instead you should use Poisson regression or a GLM with negative binomial family. – Roland Feb 14 '23 at 06:17
  • Hi, there are blind and visually impaired users of this site who interact with it using screen readers. The screen readers can't handle the equation in your screenshot. Please edit the post to include the equation as LaTeX. If it helps, we have some resources on using LaTeX on Cross Validated. – kjetil b halvorsen Feb 16 '23 at 02:00

1 Answers1

1

This is asked multiple times on site, but I cannot find a good duplicate ... As said in a comment, the intercept is the fitted value if all predictors are zero. As you have one factor variable, all predictors are zero (since you use R's standard contrasts) when the factor variable is at reference level.

A very good post going into more details is at Why is the intercept in multiple regression changing when including/excluding regressors?

kjetil b halvorsen
  • 77,844