2
$\begingroup$

I have a data set of 22000 authors and I wish to compare female and male authors with regard to number of received citations, number of reads, etc. However, as the number of citations, etc., is positively skewed and there are many zeros, my distributions are not normal. So, I used Box-Cox transformation to try to normalize my data and be able to use t-test. As I have zeros, first, I added 1 to all citations, number of reads, etc. and then used the transformation. For some of my variables the transformation works and my distribution is normal. However, for some variables the distribution is not normal yet. So, I don't know what to do in this case.

$\endgroup$
4
$\begingroup$

I would recommend not transforming at all and not using a t-test.

Instead, use a count regression model; if you have a lot of 0's and skewed distributions, then a zero inflated negative binomial model might be a good choice.

$\endgroup$
  • $\begingroup$ Do you mean fitting a model for make and female? Then compare the coefficients for each model with say likelihood ratio test? $\endgroup$ – SmallChess Feb 11 '17 at 18:23
  • $\begingroup$ No. Run a regression with citations as the dependent variable and sex as one of the independent variables. $\endgroup$ – Peter Flom - Reinstate Monica Feb 12 '17 at 13:53
  • $\begingroup$ Dear Peter, Thank for the answer. I wish to compare female and male authors in terms of number of citations, number of reads, etc. So , is it possible to compare means of two groups using regression models? Please advise. $\endgroup$ – Tahereh Dehdarirad Feb 12 '17 at 14:16
  • $\begingroup$ Yes. That is perfectly possible. $\endgroup$ – Peter Flom - Reinstate Monica Feb 12 '17 at 15:01
  • $\begingroup$ Ah. interesting. How can i do that? As you suggested, citations as the dependent variable and sex as one of the independent variables? In this case still can I say I used regression models to compare female and male authors? Is there any sample paper with this regard? Please advise! $\endgroup$ – Tahereh Dehdarirad Feb 12 '17 at 15:18

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.