Get premium membership and access revision papers, questions with answers as well as video lessons.

Got a question or eager to learn? Discover limitless learning on WhatsApp now - Start Now!

Microeconometrics Question Paper

Microeconometrics

Course:Master Of Arts In Economics

Institution: Kenyatta University question papers

Exam Year:2009

KENYATTA UNIVERSITY
UNIVERSITY EXAMINATIONS 2009/2010
FIRST SEMESTER EXAMINATION FOR THE DEGREE OF MASTER OF
ECONOMICS
EES 505: MICROECONOMETRICS

DATE: Thursday 3rd December, 2009
TIME: 9.00 a.m. – 12.00 noon

INSTRUCTIONS
Answer all FOUR questions.

Question 1
(a)
(i)
Differentiate between Random effect and Fixed effect models.
[2.5
marks]
(ii)
What are the assumptions that are made in each of the models in part (i)
above?
[4
marks]
(b) Given
yit = ?i + Xßit + uit, where ?i denotes unobservable Random variable
specific to cross sectional section I, uit denotes error term which is identically and
independently distributed, yit is a scalar of dependent variables, X is a vector of
independent variables, show that pooled ordinary least square estimator yields
biased
and
inconsistent
estimates.
[7
marks]
(c)
Suppose you have T = 2 years of data on the same group of N working
individuals. Consider the following model of wage determination:

Log(wage )
=?
+ ? d2

+ z
'?
+ d female
+ d d2 female
x
+ c + e
it
1
2
t
it
1
i
2
t
i
i
it

The unobserved effect, ci is allowed to be correlated with zit and with femalei.
The variable d2 is a time period indicator; d2t = 1 if t = 2 and 0 if t = 1. In what
follows: assume that
E[e female

, z z
,
c
,
=
=

it
i
i1
i2
i ]
t
0,

2

1,

(i)
Without further assumptions, what parameters in the log wage equation
can be consistently estimated?

[2 marks]
Page 1 of 3

(ii)
Interpret the coefficients ?1 and ?2.

[2 marks]

Question 2
(a)
Giving examples, differentiate between ordered choice models and count data
models.

[4 marks]
(b)
The probit results of the estimated coefficients of data on automobile and public
transportation travel times and the alternative chosen for T=21 individuals are
given as follows:
b + b
x = -

0.0644

+ 0.0299 x

1
2
i
i
t -

values

(-.161)
(2.916)

Where the variable xi = (bus time – automobile time) and the dependent variable
yi = 1 if automobile transportation is chosen.
Required:
(i)
Interpret the signs of b1 and b2.

[2 marks]
(ii)
What is the magnitude of the effect of increased public transportation time
given that travel via public transportation currently takes 20 minutes
longer than auto travel? Interpret your answer.

[6 marks]
(iii)
If an individual is faced with the situation that it takes 30 minutes longer
to take public transportation than to drive to work, what is the probability
that auto transportation will be selected? Comment on your answer.

[5.5 marks]
Question 3
(a)
Differentiate
between
the
following:
[8
marks]
• Fixed effects (within) and First difference estimators
• Truncated regression model and censored regression model
• Mixed logit model and Nested logit model
• Ordered multinomial model and sequential multinomial models
(b)
Explain how elasticities are calculated under the multinomial logit model.

[4 marks]
(c)
A simple labor market equation is estimated using pooled least squares results, the
Fixed effects results and the Random effects models. Based on the results given
below, which model do you think the analyst should report as their best estimates,
the pooled least squares results, the Fixed effects results or the Random effects
results? Justify your answer with the statistical evidence.
[5.5 marks]
Page 2 of 3

|Lagrange Multiplier Test vs. Model (3) = 21472.90|

|(1df, prop value = .000000)

|Fixed vs. Random Effects (Hausman) = 137.97|

Question 4
(a)
State and explain 2 limitations of linear probability models. How can these
limitations
be
solved?
[5.5
marks]
(b)
While estimating a Fixed effects model, an analyst notices that R2 jumps from an
unimpressive 0.08 to a very impressive 0.66 when the dummy variables for the
Fixed effects model are added to the equation. This seems like a very large
change just for a set of constants. Should this be expected? Explain.

[3 marks]
(c)
The following table shows a Binary logit model results estimated from
automobile and public modes of transport.
Variable Name
Coef. Estimate
Standard Error
t statistic
Auto Constant
1.45
0.393
3.70
In-vehicle time (min)
-0.00897
0.0063
-1.42
Out-of-vehicle time (min)
-0.0308
0.0106
-2.90
Out of pocket cost*
-0.0115
0.00262
-4.39
Transit fare**
0.00708
0.00378
-1.87
Auto ownership*
0.770
0.213
3.16
Downtown workplace*
-0.561
0.306
-1.84
(indicator variable)

*auto specific variable; **transit specific variable

Required:
(i)
Which is the preferred mode of transport? Justify your answer.
[3 marks]

(ii)
Interpret the coefficients of each of the independent variables.

[6 marks]
……………………….
Page 3 of 3

Microeconometrics Question Paper

More Question Papers

Popular Exams