# Re: st: Time series with moving average growth rate

 From Robert A Yaffee To statalist@hsphsun2.harvard.edu Subject Re: st: Time series with moving average growth rate Date Tue, 03 Jun 2008 13:18:02 -0400

```Dear Marcello and Humnath,

You have to be clear about whether your terminology is conventional or not.
For the conventional meaning of a moving average, the answer to your
question would be as follows:

You can easily generate a 3 month moving average after tssetting your
data, with the command

tssmooth ma newvarname=country1, window(3,1,0)

or

tssmooth ma newvarname=country1, window(3,0,0)

depending on whether you wish the current observation included in the moving average.

for each country separately, though I have done it only for country1 here..

If you mean that you wish to average the three country scores, and then compute a regression on time
then the answer would be quite different.   In that case the answer would be quite different.
You might wish to use a prais regression on time.

Regards,
Bob Yaffee

Robert A. Yaffee, Ph.D.
Research Professor
Silver School of Social Work
New York University

----- Original Message -----
From: Marcello Pagano <pagano@hsph.harvard.edu>
Date: Tuesday, June 3, 2008 10:37 am
Subject: st: Time series with moving average growth rate
To: statalist@hsphsun2.harvard.edu

> *************************
>
> Dear list members,
>
> I have time series data (2000-2007) on crop yield for three countries.
> I
> would like to calculate 3-year moving average   growth rate for each
> country, i.e. one year increase in every subsequent period (e.g.
> 2000-02, 2001-03,.....2005-07). My equation is log(yield) = a +
> b(time).
> The growth rate is (b*100). I would like to write a loop command or
> any
> other procedure which produce 3-year moving average growth rate for
> entire period ( six values in this case) for each country. I would be
>
> grateful if anyone from this list can help me in this regard. The
> hypothetical data is given below.
>
>
> Year   country1   country2   country3
>
> 2000   1.6    1.1    1.8
>
> 2001   1.7    1.2    1.9
>
> 2002   1.9    1.1    2.0
>
> 2003   2.1    1.3    2.1
>
> 2004   2.4    1.5    2.6
>
> 2005   2.7    1.8    2.5
>
> 2006   3.1    2.1    2.9
>
> 2007   3.5    2.3    3.2
>
>
>
> Sincerely,
>
> Humnath Bhandari,
>
> IRRI, Philippines
>
> *
> *   For searches and help try:
> *   http://www.stata.com/support/faqs/res/findit.html
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/
```