Statistical tests

Question 1

what does the overidentification test for IV do?

Answer 1

tests for instrument validity

Question 2

what is the test for IV instrument validity?

Answer 2

overidentification test

Question 3

what is the null of the overidentification test?

Answer 3

all instruments are valid

Question 4

what does it mean if you reject the null for the over id test?

Answer 4

one or more instruments are not valid or model was misspecified

Question 5

true or false: if you reject the null for the iv test (that all instruments are valid), then you have proof that the instruments are valid

Answer 5

a lack of rejection should not be interpreted as confirmation of validity.

Question 6

How do you test for whether you need to use IV (meaning you have an endogegnous regressor)?

Answer 6

Hausman test

Question 7

What is the null of the Hausman test for IV?

Answer 7

you don’t need to use IV–variables are exogenous

Question 8

wha does it mean if you reject null of Hausman test for IV?

Answer 8

explanatory variable is endogenous and IV is appropriate

Question 9

what does it mean if you fail to reject null of Hausman test for IV?

Answer 9

You should use OLS, because IV is less efficient than OLS

Question 10

what is hausman test in context of FE?

Answer 10

testing whether you should use FE or RE

Question 11

what is the null of the hausman test for FE?

Answer 11

Null: RE assumptions hold, both estimators consistent but RE is efficient.

Question 12

what should you do if you reject null of hausman test for FE?

Answer 12

RE assumptions do not hold and the RE estimator

is inconsistent–you should use FE

Question 13

true or false: If you fail to reject null of hausman test for FE, you can use RE

Answer 13

true

Question 14

What is the null for the f test in general?

Answer 14

coefficients are jointly zero

Question 15

how do you test for weak IV instruments?

Answer 15

F test

Question 16

what is the null for the f test of weak instruments?

Answer 16

instruments in the first stage are weak

Question 17

what does it mean if you reject f test for weak instruments?

Answer 17

instruments explain variation in endogenous variables–

Question 18

what does it mean if you fail to reject the null of the test for weak instruments?

Answer 18

You need to find a betterr instrument

Question 19

what is the general rule of thumb for test of weak instruments (value greater than __)?

Answer 19

10–if it’s greater than 10, it is not a weak instrument

Question 20

How do you use f test in context of RD?

Answer 20

to see if there are other points of discontinuity

Question 21

what is the null of the f test in context of rd (checking for other points of discontinuity)?

Answer 21

There are not other points of discontinuity–dummies at other percentiles are not stat sig

Question 22

what does it mean if you reject the f test in context of rd (checking for other points of discontinuity?)

Answer 22

there are other points of discontinuity–the relationship between x and y is not smooth

Question 23

in propensity score matching, for the balance test, what is the null of the t test?

Answer 23

the means of the two groups (T and C) are equal

Question 24

what does it mean if you reject null for balance test?

Answer 24

means of the two groups are no equal

Question 25

how do you test for manipulation in RD?

Answer 25

mccrary test-is there clumping?

Question 26

what tests can you use to test for heteroskedasticity?

Answer 26

Breush-Pagan, White

Question 27

what is the null of the breusch-pagan test

Answer 27

model is homoskedastic

Question 28

what does it mean if you reject the null of breusch-pagan?

Answer 28

you have heteroskedasticity–use robust standard errors!

Question 29

how do you calculate the variance inflation factor?

Answer 29

1/(1-R^2j)

Question 30

what is the measure for multicollinearity?

Answer 30

VIF

Question 31

If VIF is less than 4, should you be worried about multicollinearity?

Answer 31

no

Question 32

If VIF is greater than 10, should you be worried about multicollinearity?

Answer 32

yes