03EstimationCb

03EstimationCb - Estimating Estimable Functions of We now...

Info iconThis preview shows pages 1–5. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Estimating Estimable Functions of We now shift attention from E ( y ) to the parameter vector . Remember our t-test questions about 1- 2 and y 1- y 2 ? Those are questions about or linear combinations of . Weve seen some models where there is a unique solution for so the elements of can be interpreted. Weve seen other models where there are an infinite number of solutions for . There are other models where some components of have unique solutions and other components have an infinite number of solutions. How can we tell when a component of is unique? How can we tell when a linear combination of is unique? What can we say about the statistical properties of solutions for ? Copyright c 2011 Dept. of Statistics (Iowa State University) Statistics 511 1 / 19 The Response Depends on Only through X In the Gauss-Markov or Normal Theory Gauss-Markov Linear Model, the distribution of y depends on only through X , i.e., y ( X , 2 I ) or y N ( X , 2 I ) If X is not of full column rank, there are infinitely many vectors in the set { b : Xb = X } for any fixed value of . Thus, no matter what the value of E ( y ) , there will be infinitely many vectors b such that Xb = E ( y ) when X is not of full column rank. The response vector y can help us learn about E ( y ) = X , but when X is not of full column rank, there is no hope of learning about alone unless additional information about is available. Copyright c 2011 Dept. of Statistics (Iowa State University) Statistics 511 2 / 19 Treatment Effects Model Remember the dairy cow experiment: six experimental units randomly assigned to two treatments. One possible model for the response is called an effects model . y ij = + i + ij , i = 1 , 2 ; j = 1 , 2 , 3 y 11 y 12 y 13 y 21 y 22 y 23 = + 1 + 1 + 1 + 2 + 2 + 2 + 11 12 13 21 22 23 y 11 y 12 y 13 y 21 y 22 y 23 = 1 1 1 1 1 1 1 1 1 1 1 1 1 2 + 11 12 13 21 22 23 Copyright c 2011 Dept. of Statistics (Iowa State University) Statistics 511 3 / 19 Treatment Effects Model (continued) In this case, it makes no sense to estimate = [ , 1 , 2 ] because there are multiple (infinitely many, in fact) choices of that define the same mean for y ....
View Full Document

This note was uploaded on 02/11/2012 for the course STAT 511 taught by Professor Staff during the Spring '08 term at Iowa State.

Page1 / 19

03EstimationCb - Estimating Estimable Functions of We now...

This preview shows document pages 1 - 5. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online