Register to reply

Multivariate linear regression

by Trilli@n
Tags: linear, multivariate, regression
Share this thread:
Trilli@n
#1
May22-10, 03:02 AM
P: 2
I have a model y= beta0 + beta1 x1 + beta2 x2 + eps, eps~N(0,1).

How to test hypothesis beta1=0 ? Is the same test for beta2=0?
Phys.Org News Partner Science news on Phys.org
Suddenly, the sun is eerily quiet: Where did the sunspots go?
'Moral victories' might spare you from losing again
Mammoth and mastodon behavior was less roam, more stay at home
Damned charming :)
#2
May22-10, 06:35 AM
P: 66
you can use a t test just like you do in simple linear regression,
except the degrees of freedom is n-3 not n-2,
You can test each variable separately.

you have to be careful about any conlcusions you make for example if x1 and x2 are highly correlated.
Trilli@n
#3
May31-10, 05:36 PM
P: 2
Can someone help me to do this in SAS?
Is this correct?

PROC REG DATA = dataset;
MODEL y = x1 x2;
test x1=0 ;
test x2=0;
run;

How can I save p value from each test to a new data?


Register to reply

Related Discussions
Regression SS in multiple linear regression Set Theory, Logic, Probability, Statistics 2
Multivariate regression for project cost estimates Set Theory, Logic, Probability, Statistics 6
Linear regression in R Programming & Computer Science 3
Multivariate Linear Regression With Coefficient Constraint Set Theory, Logic, Probability, Statistics 5