I have data that I plotted with a normal distribution and a QQ plot. I was wondering especially in QQ plot it seems that 95.4% of the data is normally distributed.

My question is what does numbers meanings that above 2 sigmas in QQ plot? Should remove them or I need to transform this variable and make it more normally distributed?

enter image description here

enter image description here


The normal distribution is a theoretical model of data. Empirical data can be distributed more similarily or more dissimilarly to a normal distribution.

That empirical data has a couple of notable divergences from a theoretical normal distribution:

  • Presence of outliers
  • Not symmetric
  • Relative "peakedness"

Depending on your goal, you can pick a better model or transform the data to fit the normal distribution model. The power-law distribution might be a better model for the data. If you want to transform the data to better fit to a normal distribution, you can drop the outliers and then apply a log transformation.

  • $\begingroup$ Thanks that's an excellent explanation. $\endgroup$ – Alexander Aug 31 '19 at 17:55

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.