1

I am trying to predict incidence rates of prostate cancer based on different age groups and time (in years). I am not sure which regression method to take. Some have suggested linear regression while others suggest poisson regression as I am dealing with counts (incidence rates). Appreciate your feedback! :)

Thanya
  • 11
  • Welcome! Can you possibly post some example data and explain why you want to run a regression. Please also explain exactly what you mean by "time" in this context. – tristan Apr 03 '15 at 05:27
  • See https://stats.stackexchange.com/questions/142338/goodness-of-fit-and-which-model-to-choose-linear-regression-or-poisson/142353#142353 – kjetil b halvorsen Mar 06 '20 at 12:42

1 Answers1

1

Poisson regression is likely what you are looking for because it models count data which is what you have.

One reason this is better than linear regression is because linear regression assumes errors are normally distributed around the mean and consequently your model allows negative counts. For example, if linear regression predicts an expected incidence rate of 0 then your model says an incidence rate of 1 is just as likely as -1. This is especially pertinent to you since your counts are incidence rates of prostate cancer and they will presumably be small.

As an additional note, if your data has lots of zeros look into zero inflated Poisson models. A lot of people don't develop prostate cancer and I wonder if your data includes those people.

TrynnaDoStat
  • 8,124
  • I understand it's more correct to say "in a neighborhood around 1" but I leave this here as a comment rather than in the answer because I think it'll be more beneficial to the OP this way. – TrynnaDoStat Apr 03 '15 at 12:04