Topic 12: Misspecification Flashcards Preview

ECON2271 Business Econometrics > Topic 12: Misspecification > Flashcards

Flashcards in Topic 12: Misspecification Deck (12)
Loading flashcards...
1

What kind of misspecification errors can occur?

-Omitting a relevant variable

-Including an unnecessary or irrelevant variables

-Measurement error

-Other things we don't care about

 

2

What is the result of omitting a relevant variable?

- Bias estimators

- Inconsistant

- Incorrect testings

3

What is the expected value of an estimator given a relevant variable has been omitted

E(⍺2)=B2+ B3b32

4

What are the effects of including an irrelevent variable?

σstill correctly estimated

Higher variance then true model

Still BLUE

5

What can be done to detect misspecification?

-Ramsey's RESET test

-LM Test

6

Explain the Ramsey's RESET test

If there is mis-speciication, there may be a apattern between Yi^ and the residuals. 
So introducing Yi^ or polynomial forms might improve fit

Run the regression with and without.

7

Give the equation for the RESET test, and state it's distribution

 

df = # new regressors, n - # total parameters in new regression

8

Problems with the Ramsey RESET test?

Doesn't specify the alternate model

9

Explain the LM Test

The Lagrange Multiplier test for adding variables.

1. Run normal regression, get residuals

2. regress residuals on all regressors, normal and with the considered variables

3. nR2 ~ chi (number of omitted variables)

His the restricted model, no new variables

10

What is the result of measurement error in the regressant?

More variance in the sample, assumptions all fine, OLS still BLUE/BUE

11

Show mathematically the problem with measurement error in regressors

Yi = B2Xi*+ui

Yi=B2(Xi - ϵi) + ui

Yi=B2Xi + vi

vi = B2ϵi - ui

E(vi) = -B2ϵ

Very bad, nonzero expected error and error correlated with regressors

12

What are the implications of measurement error in regressors?

OLS estimators biased and inconsistant

- not valid for testing

-very serious problem with no good solutions, other then get accurate measurements

- some approachs, but we don't consider them

- Instrumental variables