# dave fournier

less info
reputation
4
bio website location age member for 3 years, 1 month seen Sep 5 '12 at 20:08 profile views 28

# 24 Actions

 Jan10 awarded Nice Question Jun29 comment Dealing with 0,1 values in a beta regression But they don't take this approach. They propose a different model, a mixed discrete continuous process. That is very different from binning the extreme values. As I said before if the beta model is valid then the binning model is valid. If the discrete continuous model is valid then the beta model is invalid. I suspect that they were mostly driven in their analysis by the kinds of mixed models they could fit with their software. The binned beta mixed model is a bit more difficult to fit. Jun29 revised Dealing with 0,1 values in a beta regression change the question to make it clear that I propose a different model rather than modifying the data Jun29 comment Dealing with 0,1 values in a beta regression But that does not answer my question. I am well aware that one can transform the data. My questions is why not transform the model instead? Jun29 revised Dealing with 0,1 values in a beta regression put in missing log() for log-likelihood Jun28 asked Dealing with 0,1 values in a beta regression Nov29 revised lme4 or other open source R package code equivalent to asreml-R explain that there is a difference between existing package and programmming language Nov28 suggested suggested edit on lme4 or other open source R package code equivalent to asreml-R Nov24 answered lme4 or other open source R package code equivalent to asreml-R Feb1 comment Expected number of runs of length n in coin toss Well you said a formula and 1/2 1/4 1/8 etc is certainly a formula. It seem to me it indicates a rather simple proof. Suppose you start throwing the coin and record the length of each run. the first throw is either H or T. the second throw can be H or T and the probability is 0.5 that they are it is different from the first throw. thus the probability is 0.5 that the length of the string is 1. Similarly it is 0.25 that the length of the string is 2 and so on. Feb1 comment Expected number of runs of length n in coin toss each one is 1/2 of the one before and 1/2 + 1/4 +1/8 ... =1 Feb1 comment Expected number of runs of length n in coin toss 1/4 1/8 1/16 .... Dec19 comment Non-linear model fitting in many dimensions I think that to get good advice you will need to describe your model for us. Dec15 comment No valid coefficients for NegBin regression It might require some tweaking. glmmADMB is intended to fit a Negative Binomial mixed model. It would be fairly simple to modify it for just a Negative Binomial regression. Dec14 answered No valid coefficients for NegBin regression Nov14 comment State space form of time varying AR(1) If you post some data, I'll run the model for you and see what happens. Nov12 revised State space form of time varying AR(1) A caveat Nov12 awarded Teacher Nov11 revised State space form of time varying AR(1) added 33 characters in body Nov11 awarded Editor