Re: [R] estimating rho of Poisson distributed data

2010-01-15 Thread John Sorkin
If you use fit1<-glm(y~x,offset=offset,family=poisson(link=log)) you will get values for the Null deviance and residual deviance along with degrees of freedom for these parameters. One of these deviances divided by its degrees of freedom might be what you are looking for. but I am not sure. Per

Re: [R] estimating rho of Poisson distributed data

2010-01-15 Thread David Winsemius
On Jan 15, 2010, at 9:46 AM, Titus von der Malsburg wrote: On Fri, Jan 15, 2010 at 09:19:23AM -0500, David Winsemius wrote: On Jan 15, 2010, at 5:59 AM, Titus von der Malsburg wrote: Mean and variance of Poisson distributed data are specified by \rho. How can I estimate \rho for a set of me

Re: [R] estimating rho of Poisson distributed data

2010-01-15 Thread Titus von der Malsburg
On Fri, Jan 15, 2010 at 08:33:52AM -0700, Peter Ehlers wrote: > Why would anyone complain? You're free to call it 'applesauce' > if that suits you. Good idea, I will do this from now on! ;-) > What do you mean by 'general way to fit a distribution'? > Maximum likelihood might be one way. Somebo

Re: [R] estimating rho of Poisson distributed data

2010-01-15 Thread Peter Ehlers
Titus von der Malsburg wrote: On Fri, Jan 15, 2010 at 09:19:23AM -0500, David Winsemius wrote: On Jan 15, 2010, at 5:59 AM, Titus von der Malsburg wrote: Mean and variance of Poisson distributed data are specified by \rho. How can I estimate \rho for a set of measurements in R? rho <- mean(

Re: [R] estimating rho of Poisson distributed data

2010-01-15 Thread Titus von der Malsburg
On Fri, Jan 15, 2010 at 09:19:23AM -0500, David Winsemius wrote: > > On Jan 15, 2010, at 5:59 AM, Titus von der Malsburg wrote: > > >Mean and variance of Poisson distributed data are specified by \rho. > >How can I estimate \rho for a set of measurements in R? > > rho <- mean(x) Yeah, thanks :-)

Re: [R] estimating rho of Poisson distributed data

2010-01-15 Thread David Winsemius
On Jan 15, 2010, at 5:59 AM, Titus von der Malsburg wrote: Mean and variance of Poisson distributed data are specified by \rho. How can I estimate \rho for a set of measurements in R? rho <- mean(x) David Winsemius, MD Heritage Laboratories West Hartford, CT ___

[R] estimating rho of Poisson distributed data

2010-01-15 Thread Titus von der Malsburg
Mean and variance of Poisson distributed data are specified by \rho. How can I estimate \rho for a set of measurements in R? Many thanks! Titus __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posti