st: AW: RE: Seasonal Dummies and Autocorrelation

[Beatrice Crozza <beatrice.crozza@gmail.com>]

Dear Martin and Nick,

thank you very much for your help.

This is what I did to remove seasonality from my data and then I did
again a chi square test, to check if after  this procedure there is
independence in my data:

tsset time
su  y, mean
local mu = r(mean)
cap noi gen newvar=`mu'
reg yL(1/6).y dum*, nocon
predict double ySA, residuals
replace ySA=ySA+`mu'

Then, I did again my chi square test, to see if now there is independence:

testparm L1.y L2.y L3.y L4.y L5.y L6.y dum1 dum2 dum3 dum4 dum5 dum6

Unfortunately, also after this there is dependence in my data.

However, when I checked with a graph my new seasonal  adjusted series:

tsline y ySA, lpattern (solid dash)
I saw no difference in the series!

So, I think that I did something wrong and my new series is not
seasonally adjusted.

Could you please help me to understand what I am doing wrong?

Thank you very much.

Best,
Bea
*
*   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/