Message Boards Message Boards

0
|
4632 Views
|
3 Replies
|
0 Total Likes
View groups...
Share
Share this post:

[?] Calculate confidence interval for an expected value in linear model?

Posted 6 years ago

Hi everyone

I'm sure there is a really simple solution for my problem but I just can't figure it out.

After using LinearModelFit to estimate a mode (lm)l, I calculated an expected point estimate using some fixed values (lm[1,2,3]). I'd now like to calculate a confidence interval for my point estimate. What would be the way to do it?

Thanks

POSTED BY: Luka Vucicevic
3 Replies

An explicit example would be helpful here. That should include some indication of the desired result.

POSTED BY: Daniel Lichtblau
Posted 6 years ago

Hi Daniel

Thanks for the reply. So after estimating a model, I get a value of lets say 13 - I now want the 95% CI for this value, so what I'm searching for is basically a confidence interval for a point estimate. Does that make sense?

Thanks

POSTED BY: Luka Vucicevic

Luka,

I think what you want is in the documentation here: LinearModelFit

Search for "MeanPredictionConfidenceIntervalTable" in the examples and read the next few sections-- it shows how to get a table of confidence bands and even confidence functions for a given ConfidenceLevel with MeanPredictionBands.

As Daniel posted, to be of any more help, you would be best to give an actual example with some data and what specifically you are trying to do.

Regards,

Neil

POSTED BY: Neil Singer
Reply to this discussion
Community posts can be styled and formatted using the Markdown syntax.
Reply Preview
Attachments
Remove
or Discard

Group Abstract Group Abstract