Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: Collapsing daily data to a monthly data on the 15th each month
From
Toby Knapen
To
[email protected]
Subject
Re: st: Collapsing daily data to a monthly data on the 15th each month
Date
Wed, 22 Jan 2014 13:23:39 +0100
Thank you Nick for the very useful reply!
Unfortunately I'm still struggling with the second command:
replace target = mdy(<month>, 16, <year>) in 1
As you described, there is some surgery needed, because not every
month has a 16th day(business days). Problem is that I can't adapt
this manually as I have data for 10 years and for 400 firms (about 1.5
million observations).
Hopefully you can help me out how to fix this. Thank in advance!
Toby
On 21 January 2014 18:56, Nick Cox <[email protected]> wrote:
> Let's identify each month by a start date that is 16th of each month
> and each year.
>
> The target starts are
>
> gen target = date if day(date) == 16
>
> Some surgery will needed at the beginning to enter an appropriate
> target for observation 1 if the first day is not the 16th.
>
> replace target = mdy(<month>, 16, <year>) in 1
>
> Then we copy each target by
>
> replace target = target[_n-1] if missing(target)
>
> then -collapse ... , by(target)-
>
> Nick
> [email protected]
>
>
> On 21 January 2014 17:42, Toby Knapen wrote:
>> Dear Statalisters,
>>
>> I would like to transform my daily data to monthly data, calculated on
>> the 15th of each month, more precisely, from the 16th day of a
>> specific month up to and including the 15th day of the following
>> month. The problem is that I can only find the way to this it based on
>> 'regular' months. This can be done by using the following commands:
>>
>> g dm=mofd(date)
>> format dm %tm
>> collapse prc ret shrout vwretd ewretd, by (dm)
>> tsset dm, monthly
>>
>> Since I'm having inflation dates on the 15th each month I would like
>> to have the monthly data on the 15th as well, otherwise there will be
>> a mismatch in my data. The data on my dates looks like below:
>>
>> 16dec2002
>> 17dec2002
>> 18dec2002
>> 19dec2002
>> 20dec2002
>> 23dec2002
>> 24dec2002
>> 26dec2002
>> 27dec2002
>> 30dec2002
>> 31dec2002
>> 02jan2003
>> 03jan2003
>> 06jan2003
>> 07jan2003
>> 08jan2003
>> 09jan2003
>> 10jan2003
>> 13jan2003
>> 14jan2003
>> 15jan2003
>> 16jan2003
>> 17jan2003
>> 21jan2003
>> 22jan2003
>> 23jan2003
>> 24jan2003
>> 27jan2003
>> 28jan2003
>>
> *
> * 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/