Time series autocorrelation: Bartlett's formula
Posted: Fri May 30, 2014 2:16 am
Dear all,
I'm sorry if the question sounds elementary, but i'm new to Eviews and econometrics world.
I'm working on more than 300 series and, after looping an ADF test for each serie, i would like to test whether the series are autocorrelated or not.
In order to do that, I've decided to verify if the autocorrelation coefficients of each correlogram (max lag=10) lie outside or inside the Bartlett's bands.
Do you guys have an idea on what to do?
Thanks in advance
I'm sorry if the question sounds elementary, but i'm new to Eviews and econometrics world.
I'm working on more than 300 series and, after looping an ADF test for each serie, i would like to test whether the series are autocorrelated or not.
Code: Select all
group g * 'put every series in the workfile into a group
g.drop resid
table ADF
for !i=1 to g.@count 'loop through every series in the first group
%name = g.@seriesname(!i) 'grab the current series name
uroot(adf, const, dif=0,info=sic,save=level1) {%name}
ADF(1,1+!i)=%name
ADF(2, 1+!i)= level1(4,1)
next
Do you guys have an idea on what to do?
Thanks in advance