QE

Question 1

F-Test Formula

Answer 1

Careful on your definiton of K

[n-k-1/q] [TSS-RSS/TSS]
^all unrestricted model.
RSSrest = TSSunrest

k is number of regressors, q is restrictions

Speciffy it as the homoskedastic only F-test

Question 2

Confidence Interval Values

Answer 2

90% - 1.645
95% - 1.96
99% - 2.58

Question 3

Standard Error Forumla

Answer 3

sigma/sqrt(n)

Question 4

Variance formulae

Answer 4

Var(X)=E[(X-mu )^2]

= E[X^2] - E[X]^2

Question 5

Covariance formulae

Answer 5

E(XY) - E(X)E(Y)

= E(X-E(X))(Y-E(Y)

Question 6

R^2 Formula

Answer 6

1 - (SSR/SST)

Question 7

Adjusted R^2

Answer 7

1 - [(n-1)/(n-k-1)] [SSR/SST]

Question 8

LATE Assumptions

Answer 8

MIRE

like quagMIRE

Question 9

LATE Definition

Answer 9

Average causal effect on COMPLIERS

Question 10

TOT

Answer 10

Treatment effect On the Treated

WEIGHTED average of the causal effect on COMPLIERS and the causal effect on ALWAYS TAKERS

Question 11

TOU

Answer 11

Treatment effect On the Untreated

WEIGHTED average of the causal effect on COMPLIERS and the causal effect on NEVER TAKERS

Question 12

Bloom Result

Answer 12

If no never takers, LATE = TOT

Question 13

5 Threats to internal validity

Answer 13

HIPCA

Individualistic treatment response (each person’s outcome depends only on his own treatment), contamination, Hawthorne effect, placebo, attrition

Question 14

4 Threats to external validity

Answer 14

S A S S

Sampling, spillover effects, assignment differences, short durations (surrogate outcomes).

Question 15

Type 1 Error

Answer 15

Incorrect rejection of a true null.

False positive.

Question 16

Type 2 Error

Answer 16

Incorrectly accepting a false null.

False negative

Question 17

IV Assumptions

Answer 17

Exogeneity of instrument (good as randomly assigned and exclusuion), and relevance
3 in total for QE

Question 18

Testing IV independence assumption

Answer 18

Not directly testable.

1. Distribution of covariates
2. Baseline information

Question 19

Derive Omitted Variable Bias formula

Answer 19

SRBeta = LRBeta + OVB

OVB = gamma (Cov(X,OmittedVar)/Var(OmittedVar))
OVB only does not equal to zero if
1. omitted var is correlated with outcome
2. omitted var is correlated with other instrument.

Question 20

Autocovariance

Answer 20

Cov ( Yt , Yt-1 )

What is the summation equation?

Question 21

Autocorrelation

Answer 21

Cov ( Yt , Yt-j ) / var (Yt)

Question 22

Dickey-Fuller Test

Answer 22

Test if unit root is present.
I.e. H0: Beta1 = 0

WHAT DOES THIS DO

Question 23

Chow Test

Answer 23

Testing for structural breaks

How is this done?

Question 24

Spurious regression

Answer 24

Regression that provides evidence of a non-existent relationship between two variables. I.e. two random walks regressed on each other.

Question 25

Spurious regression

Answer 25

Regression that provides evidence of a non-existent relationship between two variables. I.e. two random walks regressed on each other.

Question 26

Granger causality test

Answer 26

Testing if additional variables in a time series have predictive power.
Use an F-test with H0 that BetaX = 0.

Question 27

Problems with having a unit root/having trends

Answer 27

1 AR coeffcients are strongly biased towards zero. This leads to poor forecasts.
2 Some t-statistics do not have a standard normal distribution, even in large samples.
3 If y and x are both random walks then they can look related even when they are not - this gives us a spurious regression.

Question 28

ATT Equation

Answer 28

write it

Question 29

ATE Equation

Answer 29

write it

Question 30

what to say in a t test

Answer 30

State what you are testing and say ceteris paribus

Outline H0 and H1
Under H0, define t-stat, and say that it is approximated N(0,1) by the CLT, assuming random (iid) and large (n observations) sample).

Decision rule.

Do the test.

Answer, and ceteris paribus.

Question 31

IV Equations

Answer 31

Structural: D on Y
Reduced: Z on Y
First: Z on D

Question 32

IV Estimator

Answer 32

equation

Question 33

Contamination

Answer 33

People who arent assinged to treatment get it

Question 34

RSMFE Equation

Answer 34

?

Question 35

P Value

Answer 35

Is the chance of making a type 1 error when taking p value as your significance level