Simple linear regression with One regressor: Inference - Properties of OLS estimator under LS assumptions

6 important questions on Simple linear regression with One regressor: Inference - Properties of OLS estimator under LS assumptions

What is the Law of Iterated Expectation? Src. Bruce Hansen

See img

Define the law of total variance and explain its relevance

The law of total variance states for two random variables X and Y the following:
var(Y ) = E[var(Y |X)] + var(E[Y |X]).


So in words:
the variance of Y
=
the average of the Variance of Y given X
+
the variance of the average of Y given X

So its basically just that the variance of Y consists of 2 components:
the avg of the variances of Y|X
+
the variance of the average of Y|X

It is relevant because it is used when deriving the formula for the variance of B1-hat

Unsolved Question; on slide 16 it defines the variance as var(b1-hat), why the decision to start with var(b1-hat - b1) ?

Abc
  • Higher grades + faster learning
  • Never study anything twice
  • 100% sure, 100% understanding
Discover Study Smart

What is asymptotic normality?

Asymptotic = behavior as sample size increases (to infinity).

Then asymptotic normality = as sample sizes increases, behavior will be normal (thats what we will try to prove)

What 3 theorems will we use to proof asymptotic normality?

1. Law of large numbers
2. Central limit theorem
3. Slutsky's theorem

Under the 3 OLS assumptions, in large samples B0-hat and B1-hat are....

...approximately normally distributed

The question on the page originate from the summary of the following study material:

  • A unique study and practice tool
  • Never study anything twice again
  • Get the grades you hope for
  • 100% sure, 100% understanding
Remember faster, study better. Scientifically proven.
Trustpilot Logo