4
$\begingroup$

data from R

I don't know how to write a fitted model. What I did was: Y hat = (1.222 * e^1) + (3.938 * e^-4 * sqft_living)

This is for the fitted model for waterfront = 0 group. However, I don't know how to do it for waterfront = 1 group? Can someone please give me some advice on this?

$\endgroup$
  • 1
    $\begingroup$ Hello Mary, you look really close to your goal. Is your problem in interpreting the sqft_living:waterfront interaction term? $\endgroup$ – Roland Jul 26 at 9:40
4
$\begingroup$

Assuming that sqft_living is a numerical variable then we have

For waterfront = 0 then

Y <- 12.22 + 0.0003938*sqft_living

For waterfront = 1 then

Y <- 12.22 + 0.000393*sqft_living + 0.7814 + 0.00004796*sqft_living

The main effect for sqft_living can be interpreted as the increase in the outcome (ie the slope) associated with a 1 unit increase in sqft_living when waterfront is zero.

The main effect for waterfront can be interpreted as the difference in the intercepts (the value of the outcome when sqft_living is zero) between the two groups

The interaction can be interpreted as the difference in slope between the 2 groups.

It might be a good idea to centre the sqft_living variable if a zero value for sqft_living is not meaningful , and possibly rescale it (so that the estimate is not too small)

| cite | improve this answer | |
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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