Re: [R] Extrapolating values from a glm fit

2011-01-27 Thread Dennis Murphy
Hi: Are you trying to find something analogous to the median dose? If so, look at function dose.p() in the MASS package and see if it does what you're looking for. It can take a vector of quantiles as input. HTH, Dennis On Wed, Jan 26, 2011 at 7:52 PM, Ahnate Lim ahn...@gmail.com wrote: Dear

Re: [R] Extrapolating values from a glm fit

2011-01-27 Thread Gavin Simpson
On Wed, 2011-01-26 at 19:25 -1000, Ahnate Lim wrote: Even when I try to predict y values from x, let's say I want to predict y at x=0. Looking at the graph from the provided syntax, I would expect y to be about 0.85. Is this right: predict(mylogit,newdata=as.data.frame(0),type=response)

Re: [R] Extrapolating values from a glm fit

2011-01-27 Thread Gavin Simpson
On Thu, 2011-01-27 at 00:10 -1000, Ahnate Lim wrote: Thank you for the clarification, this makes sense now! dose.p from MASS also does the job perfectly, in returning x values for specified proportions. I'm curious, if I use the other parameter in predict.glm type=link (instead of

Re: [R] Extrapolating values from a glm fit

2011-01-27 Thread Ahnate Lim
Thank you for the clarification, this makes sense now! dose.p from MASS also does the job perfectly, in returning x values for specified proportions. I'm curious, if I use the other parameter in predict.glm type=link (instead of type=response), in the case of a logistic binomial, what does this

[R] Extrapolating values from a glm fit

2011-01-26 Thread Ahnate Lim
Dear R-help, I have fitted a glm logistic function to dichotomous forced choices responses varying according to time interval between two stimulus. x values are time separation in miliseconds, and the y values are proportion responses for one of the stimulus. Now I am trying to extrapolate x

Re: [R] Extrapolating values from a glm fit

2011-01-26 Thread David Winsemius
On Jan 26, 2011, at 10:52 PM, Ahnate Lim wrote: Dear R-help, I have fitted a glm logistic function to dichotomous forced choices responses varying according to time interval between two stimulus. x values are time separation in miliseconds, and the y values are proportion responses for one

Re: [R] Extrapolating values from a glm fit

2011-01-26 Thread Ahnate Lim
Even when I try to predict y values from x, let's say I want to predict y at x=0. Looking at the graph from the provided syntax, I would expect y to be about 0.85. Is this right: predict(mylogit,newdata=as.data.frame(0),type=response) # I get: Warning message: 'newdata' had 1 rows but