0

I am trying to fit a regression model to zero-inflated data with a lognormal distribution using r. The histogram looks like this: enter image description here

I searched a little on the net. So far I believe there is no a possibility to fit these conditions to glm. I found the gamlss function as the possibility to fit a lognormal distribution with the LOGNO family. However I get an error: "family = LOGNO, : response variable out of range" - maybe because of the zero inflation?

To make my question a little clearer: I am trying to investigate the influence of various Aminoacid combinations collected under certain conditions on a certain ratio. The ratio is my response variable plotted in the shown histogram. In the end I end up with a continuous response variable and some other categorical independent variables

Has anyone an idea how I can deal with the above-mentioned problem? I couldn't find a solution so far! Thank you!

Mats
  • 21
  • 2
  • 1
    I can't help you, but perhaps someone at Cross Validated can? – Martin Gal May 16 '20 at 17:01
  • The problem is all your zeroes -- not that there are lots of them, but that there are *any* of them (a lognormal distribution can never attain the value of 0). To check this, try adding a tiny increment to your entire vector and see if you're able to fit a lognormal curve to it. See this answer for a bit more detail: https://stackoverflow.com/questions/56972789/response-variable-out-of-range-using-gamlss-in-r-logno – Aaron Montgomery May 16 '20 at 21:58
  • If you compute ratios, is this bounded at 1 or also > 1 is allowed? – Georg M. Goerg Nov 24 '22 at 05:41

0 Answers0