You are on page 1of 6

Ques 1)

Write down with the help of graphs why the variable 'price' in the quantity demand and quantity
supply equation [Simaltaneous System] is endogenous and can not be treated as a pre-determined
variable.
2. Similarly in money demand and money supply equations (Simultaneous System), why
'income' is endogenous? Make suitable graphs.
[Hint Take Help of Gujrati]
Note: All answers must be handwritten.
Submit answers on time.

Ques 2)
1 Quantity demanded is a function of price and income.
2 Quantity demanded is a function of price and lagged price (t-1).
Write down steps of ILS. [You must Solve System of Structural Coeffs.]

Ques 3)
Create reduced-form equations and parameters of the following behavioral equations
1)

2)

3)

Ques 4)
As discussed in the class when I introduced IV method, how in the following functional form the
due to variety of reasons. Since error term includes left out observable and unobservable factors.
Some such factors may be correlated with explanatory variable (here income). Then due to some
issues we have to search for alternatives of the income. That has some desirable properties. One
candidate is ‘liquid assets’ as many economists have suggested. In this case we get another
equation of income.
Estimations: By IV-2SLS
1. Form another equation
2. Create reduce form of the problematic variable and regress it. Get predictions.
3. Replace predictions in the original structural equations.
4. Run the transformed equation.
5. Interpret the results.
With the help of basis above discussed concepts, answer the following questions:
Consider a basic model aimed at predicting the impact of owning a personal computer (PC) on
the grade point average (GPA) of graduating seniors at a large public university. The model can
be represented as follows:
GPA = β0 + β1 * PC + u, where PC is a binary variable denoting PC ownership, β0 and β1 are
coefficients, and u represents the error term.
(i) What could lead to a correlation between PC ownership and u? (ii) Elaborate on the reasons
behind the probable association between PC ownership and the annual income of parents. Does
this imply that parental income serves as a suitable instrumental variable (IV) for PC? Explain
the reasoning behind your answer. (iii) Assume that approximately half of the incoming students
were given grants to purchase computers by the university four years ago, and the selection of
students for these grants was done through a random process. Provide a detailed explanation of
how you would utilize this information to create an instrumental variable for PC. (iv) Write
down the steps of IV-2sls with variables and proper notations.

Ques 5)
If you are in charge of quality inspection at a firm where a large number of machines (100+)
produce a product, say an electric bulb. You want to observe, the average number of defective
outputs per day. You want to observe this for ten days. Can you conceptualize the above problem
in terms of population and sample concept? Use proper notations for processes and variables.
Create a hypothetical series of defective outputs for ten days. Also, comment on why this
problem is clear population versus sample elaboration is not possible in many macroeconomic
series.

Ques 6)
Consider the scenario where you aim to examine whether there is a difference in math
performance between girls attending girls' high schools and those attending coed schools. A
random sample of senior high school girls from a U.S. state has been gathered, with the math
score on a standardized test being the measured variable. The variable "girlhs" is employed as a
binary indicator denoting a girl attends a girls' high school.
(i) Which additional factors would you include in the equation? (These factors should be
realistically obtainable through data collection.)
(ii) Formulate an equation connecting the math score with "girlhs" and the supplementary factors
mentioned in part (i).
(iii) Hypothetically, if unmeasured aspects like parental support and motivation influence the
error term in part (ii), could they be associated with the "girlhs" variable? Provide a rationale.
(iv) Explore the prerequisites necessary for the count of girls' high schools within a 20-mile
radius of a girl's residence to be a valid instrumental variable (IV) for "girlhs."
(v) Imagine that the calculated reduced form for "girlhs" shows a statistically significant negative
coefficient on "numghs" (the count of girls' high schools within a 20-mile radius). Would you be
confident in proceeding with instrumental variable estimation where "numghs" serves as an IV
for "girlhs"? Elaborate on your reasoning.

Ques 7)
Suppose that, for a given state in the United States, you wish to use annual time series data to
estimate the effect of the state-level minimum wage on the employment of those 18 to 25 years
old (EMP). A simple model is
gEMPt = b0 + b1 gMINt + b2 gPOPt + b3 gGSPt + b4 gGDPt + ut,
where MINt is the minimum wage, in real dollars; POPt is the population from 18 to 25 years
old; GSPt is gross state product; and GDPt is U.S. gross domestic product. The g prefix indicates
the growth rate from year t - 1 to year t, which would typically be approximated by the difference
in the logs.
(i) If we are worried that the state chooses its minimum wage partly based on unobserved (to us)
factors that affect youth employment, what is the problem with OLS estimation?
(ii) Let USMINt be the U.S. minimum wage, which is also measured in real terms. Do you think
gUSMINt is uncorrelated with u t ?
(iii) By law, any state’s minimum wage must be at least as large as the U.S. minimum. Explain
why this makes gUSMINt a potential IV candidate for gMINt.

Ques 8)
Let gGDPt denote the annual percentage change in gross domestic product and let int t denote a
short term interest rate. Suppose that gGDPt is related to interest rates by
gGDPt = a0 + b0 + int t + b1 int t-1 + u t ,
where u t is uncorrelated with int t , int t-1 , and all other past values of interest rates. Suppose
that the Federal Reserve follows the policy rule:
int t = c0 + c1 (gGDP t-1 – 3) + v t ,
where c1> 0. (When last year’s GDP growth is above 3%, the Fed increases interest rates to
prevent an “overheated” economy.) If v t is uncorrelated with all past values of int t and u t ,
argue that int t must be correlated with u t-1 . (Hint: Lag the first equation for one time period
and substitute for gGDPt-1 in the second equation.) Which Gauss-Markov assumption does this
violate?

Ques 9)
Write down a detailed note on unit root test with all three specifications.
[Take Help from the Gujrati_Porter page 754 onwards]

Ques 10)
Draw a graph of the below process. And after taking the first difference draw the series again.
Record your observations. Have you successfully detrended data with above procedure. Why
data has been detrended after the difference? Form equations and then also take a difference and
record your observations.

Yt t

8 1

13 2

18 3

14 4

13 5

18 6

24 7

20 8

18 9

24 10

27 11

22 12
20 13

28 14

32 15

29 16

28 17

30 18

37 19

34 20

So then why we need to detrend data with regression method? What is the need of regression
based detrending?

Ques 11)
Question 1)
Write down shortcomings of DF test. [Hint: Gujrati and Porter Chapter 21]
Question 2)
How to compute Q-statistic? Write procedure and compute some Q-statistic?
[Hint: Gujrati and Porter Chapter 21]

QUES 12)
Take this data on excel and do an experiment:
1. Plot original Series
2. Plot difference series
3. Run a regression. Generate residuals and plot it. Remember these residuals are now detrended
data.
4. Record your observations.

[I need not to tell how to run regression in excel, least I can expect]

In stata

Import excel “filename.xlsx”, clear firstrow sheet (“Sheet1”)


gen time=_n
regress y time
predict resid
ren resid y_detrended
twoway line y_detrended time

You might also like