0
$\begingroup$

I am trying to run a Multiple Regression model but I am not sure what should I do to prepare the data input. In my model the dependent variable is the artificial surfaces in hectares, the independent are the GDP (monetary value) and Population (inhabitants). The histogram shows that the data is not normal distributed.

  1. I would like to know if I need to normalize the distribution of the data in order to get the "bell" curve and/or
  2. if I need to normalize the data (with the max-min or standardize).
Improve this question
$\endgroup$

1 Answer 1

Reset to default
3
$\begingroup$

Regarding 1) No, you don't. OLS regression makes assumptions about the error from the model, as estimated by the residuals, not about the variables.

Regarding 2) You don't have to; opinions vary about whether results are more interpretable on standardized data or on the raw data. I think the latter is usually more interpretable, but others disagree.

Improve this answer
$\endgroup$
0

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.