Re: [R] model non-integer count outcomes

2015-07-22 Thread Wensui Liu
Thanks Thierry What if I don't know the n in the offset term? On Wednesday, July 22, 2015, Thierry Onkelinx wrote: > If you know the number of counts (n) used to calculate the average then you > can still use a poisson distribution. > > Total = average * n > glm(total ~ offset(n), family = poiss

Re: [R] model non-integer count outcomes

2015-07-22 Thread peter dalgaard
> On 22 Jul 2015, at 06:48 , Don McKenzie wrote: > > Sorry. Central limit theorem. Or some sort of vegetarian sandwich. Celery, Lettuce, Tomato sounds almost edible with sufficient mayo. ;-) > Enough averaging and you get a normal distribution (simply stated, perhaps > too simply). If so oth

Re: [R] model non-integer count outcomes

2015-07-22 Thread Thierry Onkelinx
If you know the number of counts (n) used to calculate the average then you can still use a poisson distribution. Total = average * n glm(total ~ offset(n), family = poisson) ​ ir. Thierry Onkelinx Instituut voor natuur- en bosonderzoek / Research Institute for Nature and Forest team Biometrie &

Re: [R] model non-integer count outcomes

2015-07-21 Thread Don McKenzie
Sorry. Central limit theorem. Enough averaging and you get a normal distribution (simply stated, perhaps too simply). If so others will correct me before long. :-( Sent from my iPad > On Jul 21, 2015, at 8:52 PM, Wensui Liu wrote: > > what does CLT stand for? > >> On Tue, Jul 21, 2015 at 11

Re: [R] model non-integer count outcomes

2015-07-21 Thread Don McKenzie
Or if there are enough averages of enough counts, the CLT provides another option. > On Jul 21, 2015, at 8:38 PM, David Winsemius wrote: > > > On Jul 21, 2015, at 8:21 PM, Wensui Liu wrote: > >> Dear Lister >> When the count outcomes are integers, we could use either Poisson or >> NB regressi

Re: [R] model non-integer count outcomes

2015-07-21 Thread David Winsemius
On Jul 21, 2015, at 8:21 PM, Wensui Liu wrote: > Dear Lister > When the count outcomes are integers, we could use either Poisson or > NB regression to model them. However, there are cases that the count > outcomes are non-integers, e.g. average counts. > I am wondering if it still makes sense to

[R] model non-integer count outcomes

2015-07-21 Thread Wensui Liu
Dear Lister When the count outcomes are integers, we could use either Poisson or NB regression to model them. However, there are cases that the count outcomes are non-integers, e.g. average counts. I am wondering if it still makes sense to use Poisson or NB regression to model these non-integer out