Great Deal! Get Instant $10 FREE in Account on First Order + 10% Cashback on Every Order Order Now

De ne Ii = 1 if a family is poor and Ii = 0 if a family is not poor, and de ne a family to be poor if its income, yi, is less than L, a government de ned level. Let yi = Xi + i with i  N(0; 2). a)...

1 answer below »
De ne Ii = 1 if a family is poor and Ii = 0 if a family is not poor, and de ne a family to be poor if
its income, yi, is less than L, a government de ned level. Let
yi = Xi + i
with i  N(0; 2).
a) If you have data only on Ii and Xi, which parameters of the model are estimable and how?
b) Now assume that you observe yi but your sample consists of poor families only.
i. Derive the expected value of yi given Xi in the whole population. What is the expected value
of yi given Xi in your sample (i.e. among poor families)?ii. If you estimate the model by OLS, is your estimate of a consistent estimate of the e ect of
X?
iii. Write down the log likelihood function for this model.
c) Finally, assume that you have data on all the families. However, the income yi is missing for the
poor families. How would you estimate the e ect of X on income? Write down the log likelihood
function.
Answered Same Day Dec 26, 2021

Solution

Robert answered on Dec 26 2021
125 Votes
a) If you have data only on Ii and Xi, which parameters of the model are estimable and how?
Since we are having the information about Ii and Xi, the model can be constructed for Ii using Xi
as the predictor variable
) Now assume that you observe yi but your sample consists of poor families only.
i. Derive the expected value of yi given Xi in the whole population. What is the expected value
of yi given Xi in your sample (i.e. among poor families)?
The expected value of yi given Xi in your sample is calculated as follows
E (aU` + bV`)(cY` + dZ`) = E (acU`Y` + adV`Y` + acU`Z` + bdV`Z`)
= acE(U`Y`) + ad E(V`Y`) + ac E(U`Z`) + bd E(V`Z`)...
SOLUTION.PDF

Answer To This Question Is Available To Download

Related Questions & Answers

More Questions »

Submit New Assignment

Copy and Paste Your Assignment Here