0
$\begingroup$

How should I interpret my regression result as my independent variable is in log format and my dependent variable is standardized to a mean of zero and standard deviation of one. More specifically, is it possible to make an interpretation of the estimate in percentages?

thank you in advance.

$\endgroup$
2
  • 1
    $\begingroup$ Would you please post the raw data, or a link to the raw data, before taking logs or standardizing? $\endgroup$ Commented Jul 6, 2019 at 17:02
  • $\begingroup$ Unfortunately that is not possible. But if it is of any help all the original values are larger than zero. The logged values range from 0.02 to 4.2. $\endgroup$ Commented Jul 6, 2019 at 17:36

1 Answer 1

0
$\begingroup$

When the dependent variable is in $log(y)$ format and the independent variable is $x$, according to Wooldridge (2013:44) we have a log-level model. It's interpreted as $\%\Delta y = (100\beta_1)\Delta x$. When your $x$ now is standardized to a mean of $0$ and a standard deviation of $1$, we interpret $\beta_1$ in standard deviations.

$\endgroup$
1
  • $\begingroup$ Right, that I do understand: I suppose what I am trying to ask, is if it would be possible to interpret the result as a percentage change from the cumulative normal distribution? Or am I just being crazy here? $\endgroup$ Commented Jul 6, 2019 at 17:40

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.