ECON:313-Assignment 1 1

The assignment is due by wednesday (30th july), 11 PM IST. The answers must be uploaded
in PDF format with the following filename structure:
NameLastnameAssignment1.pdf
You will have only two attempts to upload the file. Each answer should be as brief as possible.
Long answers will receive negative marking. Any form of cheating or copying will lead to a
zero grade.

Late Submissions: Assignments can be submitted late on Canvas until the available date. How-
ever, appropriate deductions will apply to all late submissions.

Note: Attach the .do file for relevant questions in the appendix of your PDF submission.
Q.1 Ref,Watson and Stone, chap-12 page no-464
That is, how much does a woman’s labor supply fall when she has an additional child? In this
exercise, you will estimate this effect using data for married women from the 1980 U.S. Census.
The data are available on the text website, http://www.pearsonglobaleditions.com, in the file
Fertility and described in the file Fertility Description. The data set contains information
on married women aged 21–35 with two or more children.
a. Regress weeksworked on the indicator variable morekids, using OLS. On average, do women
with more than two children work less than women with two children? How much less?
b. Explain why the OLS regression estimated in (a) is inappropriate for estimating the causal
effect of fertility (morekids) on labor supply (weeksworked).
c. The data set contains the variable samesex, which is equal to 1 if the first two children are
of the same sex (boy–boy or girl–girl) and equal to 0 otherwise. Are couples whose first two
children are of the same sex more likely to have a third child? Is the effect large? Is it
statistically significant?
d. Explain why samesex is a valid instrument for the IV regression of weeksworked on morekids.
e. Is samesex a weak instrument?
f. Estimate the IV regression of weeksworked on morekids, using samesex as an instrument.
How large is the fertility effect on labor supply?
g. Do the results change when you include the variables age, black, hispan, and othrace in
the labor supply regression (treating these variables as exogenous)? Explain why or why not.
Q.2 Use the data in CARD.RAW for this exercise.
(a) In Table 15.1, the difference between the IV and OLS estimates of the return to education
are economically important. Obtain the reduced form residuals, û, from equation (15.32).
(See Table 15.1 for the other variables to include in the regression.) Use these to test whether
educ is exogenous; that is, determine if the difference between OLS and IV is statistically
significant.
(b) Estimate the equation by 2SLS, adding nearc2 as an instrument. Does the coefficient on
educ change much?
(c) Test the single overidentifying restriction from part (a).

1
ECON:313-Assignment 1 2

Q.3 Ref,Wooldridde, chp-15,Page No:550

Econometrics Exercise Using HTV.RAW Data
(i) Run a simple OLS regression of log(wage) on educ. Without controlling for other factors,
what is the 95% confidence interval for the return to another year of education?
Model specification:
log(wage) = β0 + β1 educ + u

(ii) The variable ciuti, in thousands of dollars, is the change in college tuition facing students
from age 17 to age 18.
• Show that educ and ciuti are essentially uncorrelated
• What does this say about ciuti as a possible IV for educ in a simple regression analysis?
(iii) Extend the simple regression model:

log(wage) = β0 + β1 educ + β2 exper + β3 exper2 + Regional Dummies + Urban Indicators + u

• Include quadratic in experience

• Full set of regional dummy variables for current residence and residence at age 18
• Urban indicators for current and age 18 residences
• Report the estimated return to a year of education
(iv) Using ciuti as a potential IV for educ:
• Estimate the reduced form for educ (including all explanatory variables from part iii)
• Show that ciuti is now statistically significant in the reduced form for educ
(v) Estimate the model from part (iii) by IV:
• Use ciuti as an IV for educ
• Compare the confidence interval for the return to education with the OLS CI from part
(iii)
(vi) Discussion question:
• Do you think the IV procedure from part (v) is convincing?
• Consider both the relevance and exogeneity of the instrument
Q.4 Derive and calculate the follwings
a. Starting from the expression
β̂ = (X ′ X)−1 X ′ y
and given model
y = Xβ + u
show that the derivation leads to

β̂ − β = (X ′ X)−1 X ′ u

2
ECON:313-Assignment 1 3

b. Use the above result to derive the variance-covariance matrix of β̂.

c. Using matrix algebra, calculate β̂ and Var-Cov(β̂) matrix if Y , X2 and X3 take values given
by the vectors:      
3 1.0 1.0
Y = −3.1 , X2 = −1.0 , X3 = 0.1
−1 −1.0 −2

d. Write down R2 using matrix notation and find its value.

Q.5 Ref,Watson and Stone, chap-12 page no-462
Consider the regression model with a single regressor:

Yi = β0 + β1 Xi + ui .

Suppose that the least-squares assumptions are satisfied.

a. Show that Xi is a valid instrument. That is, show that Key Concept 12.3 is satisfied with
Zi = Xi .
b. Show that the IV regression assumptions in Key Concept 12.4 are satisfied with this choice
of Zi .
c. Show that the IV estimator constructed using Zi = Xi is identical to the OLS estimator.
Q.6.
(A)Consider a simple regression model to estimate the effects of personal computer
(PC) ownership on college grade point average (GPA) for final year students at a
university:
1. Nothing that
GPAi = β0 + β1 PCi + ui (1)

where PCi is a binary variable indicating PC ownership.

(i) Explain why PC ownership may be correlated with ui ?
(ii) Explain why PC is likely to be related to parent’s annual income. Does this mean that
parental income is a good IV for PC? Why or why not?
(iii) Suppose that, two years ago, the university gave grants to buy computers to half of
the incoming students, and the students who received the grants were randomly chosen.
Explain how you would use this information to construct an instrumental variable for
PC.
(B)Ref, Bruce E. Hansen, page No-93 Consider two least-squares regressions

y = X 1β
e + ẽ
1

and
y = X 1β
b + X 2β
1
b + ê.
2

Let R12 and R22 be the R-squared from the two regressions. Show that R22 ≥ R12 . Is there
a case (explain) when there is equality R22 = R12 ?

3
ECON:313-Assignment 1 4

Q.7
In the regression model Y = β0 + β1 Xt + ut , Suppose cov(X, u) ̸= 0.
i. Show that the OLS estimate for β1 is inconsistent.
ii. If Z is an instrumental variable for X1 obtain the instrumental variable (IV) estimator
of β1 . Show that this estimator is consistent. If Z is not exogenous, then show that the IV
estimator of β1 has an asymptotic bias.
iii. If X and Z are both positively correlated with u and Corr(Z, X) > 0, how much corre-
lation would have to exist between X and u for the OLS estimator to have more asymptotic
bias than the IV estimator?

Use the following ref. to solve question 5

(Key concept 12.3) A set of m instruments Z1i , . . . , Zmi must satisfy the following two
conditions to be valid:
(a) Instrument Relevance
• In general, let X̂1i
∗ be the predicted value of X from the population regression of
1i
X1i on the instruments (Z’s) and the included exogenous regressors (W ’s), and let
“1” denote the constant regressor that takes on the value 1 for all observations.
Then
∗ ∗
(X̂1i , . . . , X̂ki , W1i , . . . , Wri , 1)
are not perfectly multicollinear.
• If there is only one X, then for the previous condition to hold, at least one Z must
have a nonzero coefficient in the population regression of X on the Z’s and the W ’s.
(b) Instrument Exogeneity
The instruments are uncorrelated with the error term; that is,

corr(Z1i , ui ) = 0, . . . , corr(Zmi , ui ) = 0.

key concept 12.4

The variables and errors in the IV regression model satisfy the following:
1. E(ui | W1i , . . . , Wri ) = 0;
2. (X1i , . . . , Xki , W1i , . . . , Wri , Z1i , . . . , Zmi , Yi ) are i.i.d. draws from their joint distribution;
3. Large outliers are unlikely: The X’s, W ’s, Z’s, and Y have nonzero finite fourth mo-
ments; and
4. The two conditions for a valid instrument in Key Concept 12.3 hold.