I will do that. but I may be back. Thanks.
From: Joshua Wiley
Cc: r-help@r-project.org
Sent: Tue, April 12, 2011 1:59:20 PM
Subject: Re: [R] Predictkion interval using regression coefficients
Hi Zeda,
The short answer to your question is no. All you have
Hi Zeda,
The short answer to your question is no. All you have are the
parameter estimates with no information on variability which you would
need to create a prediction interval. Given the great ease of fitting
models in R, I would offer to refit the model for my boss, and then
(with the model
I was given a list of parameter estimates from my boss. She wants to predict
the
dependent variable "fsshen" beyond jan 2011, the last observation, through
December 2011, giving the prediction intervals (90%). I don't know if I have
the
complete information to do this. So my question(s) is can
3 matches
Mail list logo