Applying -varsoc- command with panel data

[Anat Tchetchik]

Dear all,
I have an unbalanced panel (N=32, T=13.5) with variables such as social spending and GDP on which I need to perform the: xtunitroot fisher.
I am using the dfuller option. I can visualize the trend, however in order to determine the lag length I was using the varsoc command but it seems that is doesn't perform with panel data as I get an error massage:
varsoc socialspending
repeated time values in sample

Do I need to loop the varsoc command over all panels and choose the max lag length over all panels?
Any hint will be greatly appreciated,
Anat

[Anat Tchetchik]

Dear all,
Following my original post on how to apply -varsoc- on a panel data,
I found the following code by Scott Merryman:
use http://fmwww.bc.edu/ec-p/data/hayash...on91.dta,clear
<>
qui {
keep if country < 13
preserve
levels country, local(levels)
foreach l of local levels {
varsoc rgdp if country == `l'
matrix A = r(stats)
if `l' > 1 {
matrix C = C \ A
}
else {
matrix C = A
}
}
svmat C, name(col)
keep if HQ < .

egen id = fill(1 1 1 1 1 2 2 2 2 2)

egen minh = min(H), by(id)
gen optimal_lag = lag if minh == HQ

sort id opt
forv i = 1(5)60 {
local lag = opt[`i']
local opt_lag "`opt_lag' `" "' `lag'"
}

restore
}
levinlin rgdp, lag(`opt_lag')

<>

The code works well on the data provided for example, but when I ran it on my panel data (13 countries with T=11 ) I receive the following error:

. levinlin rgdp, lags(`opt_lag')
lags() invalid -- invalid numlist has missing values

Any idea what could have go wrong?
Thanks for any piece of advice..
Anat

[Shubham Sharma]

How to determine the optimum lag length in panel data?