Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


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

Re: st: moving average.. conditioning on a date


From   Nick Cox <njcoxstata@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: moving average.. conditioning on a date
Date   Mon, 5 Nov 2012 12:07:43 +0000

My paper should give you enough background. Please read it. If you
can't solve your problem, please come back with code that you tried
and why it doesn't give you all you want.

Nick

On Mon, Nov 5, 2012 at 11:05 AM, Francesco <cariboupad@gmx.fr> wrote:
> On 05/11/2012, Francesco <cariboupad@gmx.fr> wrote:
>> Dear Nick,
>>
>> Thank you for your quick reply.
>> Let me then be more precise : I am interested in observations that occur at
>> most T days before the current date... and the example I gave you applied
>> for observations at most 1 day before the current date.
>>
>> So if the current observation of a given individual is observed on date T,
>> I would like to consider all the observations whose date is between (T-30)
>> and T.... which do not correspond to the previous 30 observations prior to
>> date T's observation because the may be much more or less (or not at all)
>> observations that respect that rule.
>>
>> What do you think?
>> Many thanks for your help
>>
>> Le 5 nov. 2012 10:05, "Nick Cox" <njcoxstata@gmail.com> a écrit :
>>  Le 5 nov. 2012 10:05, "Nick Cox" <njcoxstata@gmail.com> a écrit :
>>
>>> Sorry, but this makes no sense to me.
>>>
>>> If the rule is at most 30 days before, then Sept 5 qualifies for Sept 7.
>>>
>>> Conversely, if the rule is at most the previous 2 days, the earlier
>>> example appears inconsistent with that rule.
>>>
>>> I leave you to work out what your rule(s) really are. In terms of
>>> Stata technique you may find
>>>
>>> SJ-7-3  pr0033  . . . . . . . . . . . . . .  Stata tip 51: Events in
>>> intervals
>>>         . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  N.
>>> J.
>>> Cox
>>>         Q3/07   SJ 7(3):440--443                                 (no
>>> commands)
>>>         tip for counting or summarizing irregularly spaced
>>>         events in intervals
>>>
>>> of use. There is a .pdf freely accessible at
>>>
>>> http://www.stata-journal.com/sjpdf.html?articlenum=pr0033
>>>
>>> Nick
>>>
>>> On Mon, Nov 5, 2012 at 8:16 AM, Francesco <cariboupad@gmx.fr> wrote:
>>> > Dear Nick,
>>> >
>>> > Many thanks for your very interesting suggestion. Tsspell should do
>>> > the job indeed
>>> > However the condition I am interested in is slighly more complicated
>>> > (at least for me) than the one I used in the above minimal example
>>> > I would like to obtain a running sum of all X's observations that
>>> > occur -at most- 30 days before the current date
>>> >
>>> >  So the example I gave was correct
>>> > 1    sep-7   1    2
>>> > because I only consider observations -at most - one day from the
>>> > current observation .. that is sep 7th and sept 6th but not sept 5th
>>> > because it is two days from sept 7th
>>> >
>>> > Do you know how to express this with Stata's lag operators?
>>>
>>> On 5 November 2012 01:48, Nick Cox <njcoxstata@gmail.com> wrote:
>>>
>>> >> If I understand this correctly, Francesco wants running sums to be
>>> >> calculated within spells of consecutive days, and separately by
>>> >> panels.
>>> >>
>>> >> Identifying spells of consecutive dates is an FAQ
>>> >>
>>> >> FAQ     . . . . . . Identifying runs of consecutive observations in
>>> panel data
>>> >>         . . . . . . . . . . . . . . . . . . . . . . . N. J. Cox and V.
>>> Wiggins
>>> >>         8/02    How do I identify runs of consecutive observations
>>> >>                 in panel data?
>>> >>
>>> http://www.stata.com/support/faqs/data-management/identifying-runs-of-consecutive-observations/
>>> >>
>>> >> One solution covered there is to use -tsspell- from SSC
>>> >>
>>> >> . tsset id date
>>> >> . tsspell, f(L.date == .)
>>> >> . bysort id _spell (_seq) : gen Y = sum(X) if _spell
>>> >> . by id _spell : gen aveY = Y/_seq
>>> >>
>>> >> Here I am guessing that the moving average required is running
>>> >> sum/number in sequence
>>> >>
>>> >> I am also guessing that the example should end
>>> >>
>>> >>  1    sep-7   1    3
>>> >>
>>> >> Note that unbalanced panels in no sense rule out the use of time
>>> >> series operators.
>>> >>
>>> >> The -egen- function -filter()- is from -egenmore- (SSC).
>>> >>
>>> >> See also
>>> >>
>>> >> SJ-7-2  dm0029  . . . . . . . . . . . . . . Speaking Stata:
>>> >> Identifying
>>> spells
>>> >>         . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
>>> >> N.
>>> J. Cox
>>> >>         Q2/07   SJ 7(2):249--265                                 (no
>>> commands)
>>> >>         shows how to handle spells with complete control over
>>> >>         spell specification
>>> >>
>>> >>
>>> >> Nick
>>> >>
>>> *
>>> *   For searches and help try:
>>> *   http://www.stata.com/help.cgi?search
>>> *   http://www.stata.com/support/faqs/resources/statalist-faq/
>>> *   http://www.ats.ucla.edu/stat/stata/
>>>
>>
>
>
> --
> Hedi BENAMAR
>
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/faqs/resources/statalist-faq/
> *   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


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