Orthogonal to this: I have some experience with rainfall
data. Daily rainfall is measured in mm. Units of ml make
no sense physically. That may be a trivial typo on
your part, but if not that correction may save you embarrassment
in the future (at the cost of some embarrassment now).
Nick
[email protected]
Scott Merryman
tssmooth ma average28 = rain, w(28)
tssmooth ma average28_2 = rain if rain !=0, w(28)
....
Patrick Woodburn
> I have weather data for a site in Uganda which I'm hope to compare to
> malaria data. My rainfall data is a single variable, sorted by date,
> with no missing data, along the following lines:
>
> date rainfall (ml)
> 01jan2003 12.7
> 02jan2003 3.0
>
> ...
>
> 31jun2007 1.3
>
> I would like to make four new variables for each date. Two to
represent
> the total rainfall across the previous 28 days and across the previous
> 84 days, and two to represent the total number of days on which
> rainfall>0 out of the previous 28 or 84 days. Could someone suggest
> how best to do this?
*
* 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/
