glm starting values not accepted log-link

r offset glm
Andi picture Andi · Nov 21, 2011 · Viewed 15.4k times · Source

I want to run a Gaussian GLM with a log link and an offset. The following problems arise:

y <- c(1,1,0,0)
t <- c(5,3,2,4)

No problem:

exp(coef(glm(y~1 +  offset(log(t)), family=poisson)))

with family=gaussian, starting values need to be specified, it works here:

exp(coef(glm(y~1, family=gaussian(link=log), start=0)))

but does not work here:

exp(coef(glm(y~1 +  offset(log(t)), family=gaussian(link=log), start=0)))

Error in eval(expr, envir, enclos) : cannot find valid starting values: please specify some"

Does anyone see what's wrong (hopefully just in my coding) ?

Answer

James picture James · Nov 21, 2011

I looks like start isn't being recognised when offset is present. You are trying to take the log of 0 in the y values which is -Inf. glm obviously cannot deal with this when looking for a solution without being given some help by start. A small perturbation in your y values will permit a solution.

exp(coef(glm(I(y+.Machine$double.eps)~1 + offset(log(t)), family=gaussian(link=log))))
(Intercept) 
  0.1481481

Related questions

ggplot2 offset scatterplot points

I have two sets of points with error bars. I would like to offset the second so it's displayed slightly down from the first set, so that it doesn't obscure the original. Here is a mock data set: x=runif(4,…

Read More
Remove rows with all or some NAs (missing values) in data.frame

I'd like to remove the lines in this data frame that: a) contain NAs across all columns. Below is my example data frame. gene hsap mmul mmus rnor cfam 1 ENSG00000208234 0 NA NA NA NA 2 ENSG00000199674 0 2 2 2 2 3 ENSG00000221622 0 NA NA NA NA 4 …

Read More
Drop data frame columns by name

I have a number of columns that I would like to remove from a data frame. I know that we can delete them individually using something like: df$x <- NULL But I was hoping to do this with …

Read More