Practicum, Questions - Homework # 2

Homework #2\r\n

Studiejaar: 2014/2015

Geüpload door:

Anonieme student

Dit document is geüpload door een student, net als jij, die anoniem wil blijven.

Erasmus Universiteit Rotterdam

Reacties

inloggen of registreren om een reactie te plaatsen.

Preview tekst

Empirical econometrics (EBC4184) Pierre Mohnen, 2014

Homework #

Use the following dataset (in .dta format)

Table F8: Income and Expenditure Data. 100 Cross Section Observations Source: Greene (1992)

 MDR = Number of derogatory reports  Acc = Credit card application accepted (1=yes),  Age = Age in years+ 12ths of a year,  Income = Income, divided by 10,000 ,  Avgexp = Avg. monthly credit card expenditure,  Ownrent = individual owns (1) or rents (0) home.  Selfempl = Self employed (1=yes, 0=no)

Take the observations where the average monthly credit card expenditures are non-zero and regress by OLS this variable on a constant, age, income and its square and a dummy for home ownership. gen income2=income^ drop if avgexp== reg avgexp age income income2 ownrent
Plot the errors on income. Do you notice any sign of heteroscedasticity?
Test for heteroscedasticity using the Breusch-Pagan Lagrange multiplier test.
Suppose i 2  2 income. How would you transform the variables to get back to

homoscedasticity after transformation?

Estimate the equation first by OLS. Are these OLS estimates of the parameters and their estimated standard errors unbiased? If so, what do you expect the direction of the bias to be.
Now estimate the equation by (feasible) GLS using the transformation recommended in question 4.
Compare the OLS and the GLS estimates of the parameters and their standard errors.
What would be the White heteroscedasticity consistent estimates of the standard errors of the OLS estimates?
Using the matrix command (MATA), try to reproduce the GLS estimates and their variance-covariance matrix using matrix expressions.

Dit is een preview

Wil je onbeperkt toegang? Word Premium en krijg toegang tot alle 3 pagina's

Toegang tot alle documenten
Onbeperkt downloaden
Hogere cijfers halen

Uploaden

Deel jouw documenten voor gratis toegang

Ben je al Premium?

Empirical econometrics (EBC4184)

Pierre Mohnen, 2014

Homework #2

Use the following dataset (in .dta format)

Table F8.1: Income and Expenditure Data. 100 Cross Section Observations

Source: Greene (1992)

 MDR = Number of derogatory reports

 Acc = Credit card application accepted (1=yes),

 Age = Age in years+ 12ths of a year,

 Income = Income, divided by 10,000 ,

 Avgexp = Avg. monthly credit card expenditure,

 Ownrent = individual owns (1) or rents (0) home.

 Selfempl = Self employed (1=yes, 0=no)

1. Take the observations where the average monthly credit card expenditures are

non-zero and regress by OLS this variable on a constant, age, income and its

square and a dummy for home ownership.

gen income2=income^2

drop if avgexp==0

reg avgexp age income income2 ownrent

2. Plot the errors on income. Do you notice any sign of heteroscedasticity?

Waarom is deze pagina onscherp?

Dit is een Premium document. Word Premium om het volledige document te kunnen lezen.

Practicum, Questions - Homework # 2

Empirical Econometrics 1 (EBC4184)

Maastricht University

Reacties

Andere studenten bekeken ook

Gerelateerde documenten

Preview tekst