PakMediNet Discussion Forum : Biostatistics : Piosson Regression for Death Data
Piosson Regression for Death Data
Dear sir,
I want to use Piosson Regression model to estimate the deaths in certain locality at different spane of time. If some have any software to solve this problem, please do reply.
Thanks
Muhammad Ibrahim
ibrahim_ap98@yahoo.com
www.biostatspk.com
Posted by: ibrahim_apPosts: 138 :: 30-03-2008 :: | Reply to this Message
Re: Piosson Regression for Death Data
I would suggest software R which is a free software and can be downloaded from this website http://cran.r-project.org/
For poisson regression you will need to use 'glm' function. You can use help in R to learn how to use 'glm' function, or you can use several resources listed on R website, or can learn from several websites that describe this function.
Posted by: rqayyumPosts: 199 :: 30-03-2008 :: | Reply to this Message
Re: Re: Piosson Regression for Death Data
Thanks for reply, but i am unable to use R software. Please guide me if you can.
Thanks
Posted by: ibrahim_apPosts: 138 :: 04-04-2008 :: | Reply to this Message
Re: Re: Re: Piosson Regression for Death Datahum! what happens, I mean, why you are unable to use it. Can you explain please?
Posted by: rqayyumPosts: 199 :: 19-04-2008 :: | Reply to this Message
Re: Re: Piosson Regression for Death DataPlease advise me how to use R sotware,as I have that one. Please send me the fuction and command to use
Posted by: ibrahim_apPosts: 138 :: 21-04-2008 :: | Reply to this Message
Re: Re: Re: Piosson Regression for Death Data
Function is 'glm'.
its usage is as noted below:
glm(formula, family = gaussian, data, weights, subset, na.action, start = NULL, etastart, mustart, offset, control = glm.control(...), model = TRUE, method = "glm.fit", x = FALSE, y = TRUE, contrasts = NULL, ...)
Here is an example of glm use for poisson regression:
> counts <- c(18,17,15,20,10,20,25,13,12)
> outcome <- gl(3,1,9)
> treatment <- gl(3,3)
> glm1 <- glm(counts ~ outcome + treatment, family=poisson())
> summary (glm1)
I hope this helps.
[Edited by rqayyum on 23-04-2008 at 12:43 PM GMT]
Posted by: rqayyumPosts: 199 :: 23-04-2008 :: | Reply to this Message