Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: VAR with Granger causal ordering
From
Karlygash Kuralbayeva <[email protected]>
To
[email protected]
Subject
st: VAR with Granger causal ordering
Date
Fri, 4 May 2012 21:10:34 +0100
Dear all:
I need to estimate a VAR with strict exogeneity assumption (or Granger
causal ordering), where the first variable is strictly exogenous:
x(t) = x(t-1) + x(t-2) + error
y(t) = x(t) + x(t-1) + x(t-2) + y(t-1) + y(t-2) + z(t-1) + z(t-2) + error
z(t) = x(t) + x(t-1) + x(t-2) + y(t-1) + y(t-2) + z(t-1) + z(t-2) + error
Note that in 2nd and 3rd equations allows for contemporaneous effect
of x(t) on endogenous variables.
I use –svar- with constraints. Why do I get the error message that I
need more identification constraints? And why do years appear in the
error message against each constraint?
Many thanks for your help.
Here is the Stata code:
gen date=yq(year, q)
format date %tq
sort date
tsset date
constraint 1 [x]L.y = 0
constraint 2 [x]L2.y = 0
constraint 3 [x]L.y = 0
constraint 4 [x]L2.y = 0
matrix A = (1,0,0\.,1,0\.,0,1)
matrix B = (1,0,0\.,.,.\.,.,.)
svar x y z, aeq(A) beq(B) lags(1/2)
Error message:
With the current starting values, the constraints are not sufficient
for identification
The constraints placed on A and B are
1992: [a_1_1]_cons = 1
1991: [a_1_2]_cons = 0
1990: [a_1_3]_cons = 0
1989: [a_2_2]_cons = 1
1988: [a_2_3]_cons = 0
1987: [a_3_2]_cons = 0
1986: [a_3_3]_cons = 1
1985: [b_1_1]_cons = 1
1984: [b_1_2]_cons = 0
1983: [b_1_3]_cons = 0
These constraints place 10 independent constraints on A and B
The order condition requires at least 12 constraints.
Identification requires a rank of 18, but the identification matrix
only has rank 15
r(498);
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/