1
$\begingroup$

My thesis supervisor advised me to show standardized coefficients in my regression output (which show the change in the dependent variable if the independent variable increases by one standard deviation). Using the "traditional" coefficients, I usually report the coefficients and the standard error in the regression output. Now I am not sure

i) whether it is common to show standard errors with the standardized coefficients (maybe it makes more sense to show the standard deviation?)

ii) how to calculate these standard errors in R. Do they even differ from the ones of the "traditional" coefficients?

For the standardized coefficients, I use the lm.beta function in R... However, with this function I only get the coefficients, but no standard errors.

Do you have any idea about this?

Improve this question
$\endgroup$

1 Answer 1

Reset to default
2
$\begingroup$

The easiest solution would be to scale your independent variable by dividing it by its standard deviation prior to model fitting. The coefficients and standard errors will then automatically be on the standardized scale.

i) You should definitely report the standard error as a measure of uncertainty. Additionally you can report the standard deviations in a descriptive analysis of the independent variables

ii) Proceed as I said above, or use the delta method, i.e. multiply the standard errors obtained through the "traditional method" by the inverse of the square of the standard deviation.

Improve this answer
$\endgroup$

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.