线性模型的复习题.pdf

回归分析复习题 1. 设P 和P 为两个投影阵，则 1 2 （1）P P =+ P 为投影阵⇔ PP P P 0 ； 1 2 1 2 2 1 （2 ）M P =− P 为投影阵⇔ PP P P P 。 1 2 1 2 2 1 2 2. 在用逐步回归的方法来选择自变量的过程中，为什么剔除自变量的显著性水平不能小于引入 自变量的显著性水平。若引入自变量的显著性水平和剔除自变量的显著性水平相等，且第一 步和第二步能引入两个自变量，试证明第三步不可能剔除任何自变量。 3. (a) Let Z , , Z be independent normally distributed random variables with E (Z ) μ , 1 n i i Var( Z ) 1. Define the non-central chi-square distribution in terms of the distribution of a random i variable C , which is some function of the Z 's. (You don't need to derive a density function, just i state that the non-central chi-square distribution is defined as the distribution of C ). What is the degrees of freedom? What is the non-centrality parameter? (b) Let Y ~ N(μ, I) ，where Y is an n × 1 random vector. Prove that if A is an n × n symmetric idempotent matrix of rank d ，then the quadratic form has a non-central chi-square distribution. Give the degrees of freedom and the non-centrality parameter (which should be given as a function of A and μ ). (c) Consider the general linear model of full rank Y Xβ + ε assuming E (ε ) 0 and 2 2 Cov(ε ) σ I and X is n × p of rank p . Derive E(S ) where 2 ˆ ˆ ˆ S (Y =− X β )'(Y − X β ) /(n − p