Heteroskedasticity & Serial Correlation Flashcards

1
Q

What is heteroskedasticity?

A

When the variance of the error term is not constant across observations.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What is the Breusch-Pagan test used for?

A

Testing for heteroskedasticity by regressing squared residuals on the regressors.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What is the null hypothesis in the Breusch-Pagan test?

A

The error variance is constant (homoskedasticity).

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What is serial correlation?

A

When the error terms are correlated across time.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What test do we use to detect serial correlation?

A

The Breusch-Godfrey (BG) test.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

How do we fix heteroskedasticity or serial correlation?

A

Use robust standard errors, GLS, or Newey-West standard errors.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Why is heteroskedasticity a problem in regression?

A

It makes standard errors invalid, which affects the reliability of t- and F-tests.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly