Bent E. Srensen
February 22, 2007
1
Teaching notes on structural VARs.
1.1
Vector MA models:
1.1.1
Probability theory
The simplest (to analyze, estimation is a dierent matter) time series models are the moving
average (MA) models:
xt = + ut + B1 ut1 + . +
Bent E. Srensen
January 23, 2007
1
Teaching notes on GMM II.
Assume that economic theory gives us the moment conditions
Eft () = 0 ,
where ft () = f (xt , ) is an r dimensional vector of moment conditions and is a q dimensional vector of parameters. The i
Bent E. Srensen
December 1, 2011
1
1.1
Teaching notes on GMM III (revised Nov 29, 2011).
Variance estimation.
Most of the material in this note builds on Anderson (1971), chapters 8 and 9. [This book
is now available in the Wiley Classics series]. In this
Bent E. Srensen
January 23, 2007
1
Teaching notes on GMM 1.
Generalized Method of Moment (GMM) estimation is one of two developments in econometrics in the 80ies that revolutionized empirical work in macroeconomics. (The other being
the understanding of u
ECONOMICS 7395, Spring 2007
Bent E. Srensen
Homework 4. February 20due February 26.
Calculate and plot the impulse response functions for the model
x1t
x2t
=
u1t
u2t
+
1 .5
.3 .2
u1t1
u2t1
+
1 2
0 .5
u1t2
u2t2
where the error terms are independent. If the
ECONOMICS 7395, Spring 2007
Bent E. Srensen
Homework 3. February 12due February 19.
Use the panel data program that I have posted. Interpret the regression results. Try and
add more lags of the right- or left-hand side variables and interpret the results.
ECONOMICS 7395, Spring 2007
Bent E. Srensen
Homework 5. March 1due March 7.
1. Ljungqvist and Sargent (2nd edition) Exercise 2.1
2. Ljungqvist and Sargent (2nd edition) Exercise 2.2
3. Ljungqvist and Sargent (2nd edition) Exercise 2.3, parts a and b.
1
ECONOMICS 7395, Spring 2007
Bent E. Srensen
Homework 2. January 24due February 5.
1. Modify the program hansin.pgm to replicate the study by Hansen and Singleton. Try
and estimate the model using 35 dierent sets of instruments. Try a set of instruments
wh