1/25
Looks like no tags are added yet.
Yi=β0+β1xi+εi, i=1,…,n.
β0 = intercept,
β1 = slope,
εi = random error.
X is known (not random); Y is random.
What are the three standard assumptions on the errors εi?
(1) E(εi)=0
(2) var(εi)=σ2 (constant)
(3) cov(εi,εj)=0 for i=j.
What do the three error assumptions mean in words?
Y depends linearly on X
The variance of Y is the same at every x
The Yi are uncorrelated.
What is the normal simple linear regression model?
yi∼N(β0+β1xi,σ2) independently, i.e. εi∼iidN(0,σ2).
Under normality, zero covariance means the Yi are independent.
What is the centred form of the model, and how are its parameters interpreted?
yi=α+β(xi−xˉ)+εi with α=β0+β1xˉ, β=β1.
Same slope; α is the mean response at x=xˉ.
What is the difference between an estimator and an estimate?
An estimator is a function of the random Yi (so a random variable).
An estimate is its value calculated from the observed data.
How can β^1 be written as a linear combination of the Yi, and why is it normal?
β^1=∑ciYi with ci=Sxxxi−xˉ, where ∑ci=0 and ∑cixi=1.
It is normal because it is a linear combination of normals.