Midterm GR5412 2019 PDF
Midterm GR5412 2019 PDF
Midterm GR5412 2019 PDF
1
3)
(30
points
total)
You
are
estimating
a
Beveridge
curve
–
the
relationship
between
the
job
vacancy
rate
and
the
unemployment
rate
-‐
with
monthly
time-‐series
data.
You
estimate
a
time-‐series
regression
of
the
job
vacancy
rate
on
the
unemployment
rate
and
a
linear
time
trend:
reg vrate urate trend
------------------------------------------------------------------------------
vrate | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
urate | -.241896 .013778 -17.56 0.000 -.2691504 -.2146417
trend | .0041129 .0007845 5.24 0.000 .002561 .0056647
_cons | 4.129086 .0675764 61.10 0.000 3.995413 4.262759
------------------------------------------------------------------------------
a) Assuming
the
data
have
not
been
seasonally
adjusted,
if,
on
average
unemployment
rates
are
higher
in
the
summer,
are
the
data
covariance-‐
stationary?
Explain
briefly,
but
carefully.
b) Are
the
data
likely
to
be
strictly
exogenous?
Briefly
explain.
If
instead,
you
had
a
data
set
from
a
cross-‐sectional
household
survey,
would
you
expect
that
data
to
be
strictly
exogenous?
Again,
explain.
c) Describe
precisely
how
you
would
construct
a
test
for
first
order
serial
correlation
in
this
model.
How
about
second
order
serial
correlation?
d) Suppose
your
test
finds
significant
serial
autocorrelation.
Are
the
OLS
estimates
above
consistent?
Unbiased?
Are
the
OLS
standard
errors
likely
to
be
correct?
e) Describe
exactly
how
you
could
use
OLS
regressions
to
estimate
a
FGLS
model
that
adjusts
for
first
order
serial
correlation.
Show
the
mathematics
and
show
that
the
approach
works.
f) Does
your
approach
in
(e)
require
additional
assumptions
in
order
to
guarantee
consistency,
as
compared
to
OLS.
g) The
dependent
variable
in
this
model
is
a
vacancy
rate.
As
such,
it
cannot
be
less
than
zero.
If
the
right
hand
side
of
the
regression
is
correctly
specified,
would
it
be
reasonable
to
assume
that
the
errors
are
normally
distributed?
Explain
briefly.
2