Exam 2019 Exercises Flashcards

1
Q

What is the definition of mixing?

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

What is the definition of stationarity? (name both)

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

What is the definition of spurios regression?

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

Name at least one strategy to solve cross-sectional dependence?

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

After pre-multiplying when setting up a CECM, how do you set up the final formula?

A

Just make sure that you do the full vector operation, which means subtracting the eq. from delta y_t

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

What is the point of a CECM model?

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

When testing for stationarity what should also be mentioned when finding that the stability condition holds?

A
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

How should a term be written that converges to zero in the limit?

A

the o_p(1)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

How should be dealt with the following?

A

It should be split up as follows, note that you need to split up S_t later on for the standard results

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

When doing the following regression, what is the result we expect for an estimate of beta?

A

We expect zero, however often with these types of exercises this is not the case

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

When dealing with the beta hat in asymptotics, how should be dealt with it?

A

We can just move it out of the sums as if it is a constant (unless it does not converge, likely)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What is a test for non-stationarity? What are the hypotheses? What does it mean to reject?

A
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Why is it not correct to estimate an ECM without the other variables?

A

Estimating the ECM for just one variable comes at the cost of loss of efficiency, therefore you should estimate the Conditional ECM conditional on the other parameters, note the estimating parameter should be weakly exogeneous to be efficient.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Why is a fixed effects estimator inconsistent for small T? (Give full description!)

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