Rolling VEC and Exogeneity

[pgupta]

Dear Team,

I have used Dynamic Cointegration (Johansen's cointegration, with a rolling window). Now I have twin objectives:
1) to estimate the rolling speed of adjustment coefficients and
2) rolling LR test statistic for rolling weak exogeneity tests.

I am not at all skilled at programming. I tried to write the following program(with the help of Rolling Regression code written by @Eviews Gareth). However, it doesn't seem to work, that is, "series lr" shows value only upto first subsample, coefmat contains only "0.0000". I would be highly obliged if you could see what all needs to be corrected. Please find attached the program file. Thank you!

smpl 1 3000
' set window size
!window = 750
' set step size
!step = 1
' get size of workfile
!length = @obsrange
'calculate number of rolls
!nrolls = @floor((!length-!window)/!step)
'matrix to store coefficient estimates
matrix(5,!nrolls) coefmat
'catching start and end points
%start = "@first" '@otod(@ifirst(ser))
%end = "@last" '@otod(@ilast(ser))
'variable keeping track of how many rolls we've done
!j=0
' move sample !step obs at a time
for !i = 1 to !length-!window+1-!step step !step
!j=!j+1
' set sample for estimation period
%first = @otod(@dtoo(%start)+!i)
%last = @otod(@dtoo(%start)+!i+!window-1)
smpl {%first} {%last}
'introduce and run vecm
var vec1.ec(b,1) 1 2 lbel lemu
' store coefficients
series alpha=vec1.a(2,1)
'save unrestricted logl for later use
freeze(test1) vec1.coint(b,2,save=mat1)
'test weak exogeneity a1=0
vec1.cleartext(coint)
vec1.append(coint) a(2,1)=0
'save restricted logl for later use
freeze(test2) vec1.coint(b,2,restrict,c=1e-5,m=100,save=mat2)
series lr=2*(mat1(1,4)-mat2(1,4))
next

[priyanshi]

Dear Team,

I have used Dynamic Cointegration (Johansen's cointegration, with a rolling window). Now I have twin objectives:
1) to estimate the rolling speed of adjustment coefficients and
2) rolling LR test statistic for rolling weak exogeneity tests.

I am not at all skilled at programming. I tried to write the following program(with the help of Rolling Regression code written by @Eviews Gareth). However, it doesn't seem to work, that is, "series lr" shows value only upto first subsample, coefmat contains only "0.0000". I would be highly obliged if you could see what all needs to be corrected. Please find attached the program file. Thank you!

smpl 1 3000
' set window size
!window = 750
' set step size
!step = 1
' get size of workfile
!length = @obsrange
'calculate number of rolls
!nrolls = @floor((!length-!window)/!step)
'matrix to store coefficient estimates
matrix(5,!nrolls) coefmat
'catching start and end points
%start = "@first" '@otod(@ifirst(ser))
%end = "@last" '@otod(@ilast(ser))
'variable keeping track of how many rolls we've done
!j=0
' move sample !step obs at a time
for !i = 1 to !length-!window+1-!step step !step
!j=!j+1
' set sample for estimation period
%first = @otod(@dtoo(%start)+!i)
%last = @otod(@dtoo(%start)+!i+!window-1)
smpl {%first} {%last}
'introduce and run vecm
var vec1.ec(b,1) 1 2 lbel lemu
' store coefficients
series alpha=vec1.a(2,1)
'save unrestricted logl for later use
freeze(test1) vec1.coint(b,2,save=mat1)
'test weak exogeneity a1=0
vec1.cleartext(coint)
vec1.append(coint) a(2,1)=0
'save restricted logl for later use
freeze(test2) vec1.coint(b,2,restrict,c=1e-5,m=100,save=mat2)
series lr=2*(mat1(1,4)-mat2(1,4))
next