I am fitting survival data with different distributions in order to determine what best characterises my data. I believe that the inverse gaussian distribution may be a good fit but I have been having trouble modelling the distribution in R. I have been using the flexsurvreg R package because it provides log likelihood and AIC values for each distribution and allows for distributions to be plotted visually. flexsurvreg does not have the inverse gaussian distribution built-in but allows for custom-made distributions. Could anyone provide a bit of help regarding how the inverse gaussian distribution could be modelled in flexsurvreg?

For a bit of reference, here is what my survival distribution looks like: enter image description here


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.