Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: RE: how to test the seasonal effect in monthly data and smooth that effect


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: how to test the seasonal effect in monthly data and smooth that effect
Date   Sun, 25 Oct 2009 15:20:46 -0000

There are many ways of investigating seasonality. I don't think it is at
all true that the literature only looks at quarterly effects, but never
month effects. 

One of the simplest and most general ways to check for seasonality is to
fit a model with no month terms and then to plot residuals from that
model against month. If there is a strong pattern, then you have
seasonality. 

Nick 
n.j.cox@durham.ac.uk 

Song Nhac (a.k.a. Pham) 

I have some questions about seasonal effect from monthly data (I
searched around but all of papers or commands are served for
quarterly). I employed Eview 6.0 (Census X11) to check and there is
seasonal effect, But I would like to use a command in Stata. How could
I solve that effect by using smoothing command in Stata for 12 periods
(month-SARIMA)?

Additionally, I did an VAR- and applied Granger Causality: the result
found the exogeneity between variables. I would like to ask that to
solve this problem, Could it be caused by seasonal effect? And how
could I solve it?


*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index