Search All of the Math Forum:

Views expressed in these public forums are not endorsed by NCTM or The Math Forum.

Notice: We are no longer accepting new posts, but the forums will continue to be readable.

Topic: Basic GLM Question
Replies: 6   Last Post: Apr 9, 2013 2:53 PM

 Messages: [ Previous | Next ] Topics: [ Previous | Next ]
 Ray Koopman Posts: 3,383 Registered: 12/7/04
Re: Basic GLM Question
Posted: Apr 9, 2013 2:53 PM

On Mar 31, 4:33 am, SChapman <sumant...@googlemail.com> wrote:
> Sorry, my question wasn't clear.
>
> Why is that in Generalised Linear Model we don't predict individual response variable values Yi? We only predict the conditional expectation E[Yi].
>
> In a general linear model (simple linear regression) however all text books give formula for predicting Yi as well as E[Yi].

If b is the vector of estimated model coefficients and x is a vector
of predictor scores for an individual then g(x'b) is the predicted
response for that individual, where g() is the inverse link function.

If C is the estimated covariance matrix of the coefficients and z
is the 1-alpha/2 quantile of the standard normal distribution then
g(x'b +/- z*sqrt(x'Cx)) is a 1-alpha confidence interval for the
response.

Look for a package that does that for you.

Date Subject Author
3/30/13 SChapman
3/30/13 Gary
3/31/13 Richard Ulrich
3/31/13 SChapman
4/9/13 Ray Koopman
3/31/13 Gary
4/1/13 David Jones