This preview shows pages 1–3. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: 1 Chapter 4 Drawing Conclusions 4.1 Understanding parameter estimates E (Y  X) = + 1 x 1 + 2 x 2 ++ p x p i : rate of change increase x i by one unit, all other x being hold constant, how much y changes. Least square regression does not mean x cause y. From the data, we only observe association between x and y. The value of a parameter estimate not only depends on the other terms in a mean function but it can also change if the other terms are replaced by linear combination of the terms. Example E (Y  X) = + 1 x 1 + 2 x 2 z = 5x 1 4x 2 E (Y  X 1 z 1 ) = * + 1 x 1 * + 2 z * 2 Rank deficient and overparameterization Aliased: a term is a linear combination of the terms already in the mean function. The coefficient for it is not estimable. Linearly dependent : a term can be expressed as a linear combination of other terms. Linear independent Making inference Experiment: some treatment applied to experimental unit....
View
Full
Document
This note was uploaded on 12/12/2010 for the course STAT 425 taught by Professor Ma,p during the Fall '08 term at University of Illinois, Urbana Champaign.
 Fall '08
 Ma,P

Click to edit the document details