<>
" You can see this using Martin's example which I modified"
Beatrice should omit the -compress- command, which starts with a capital
letter in Rajesh`s reply. It is not needed here, anyway, since I gave clear
instructions to -input- in this case. It continues to appear in my posts
because it is part of my personal "input" template.
HTH
Martin
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Tharyan, Rajesh
Sent: Montag, 7. Dezember 2009 20:57
To: [email protected]
Subject: RE: st: RE: Intraday volatility
Hi,
Others have pointed out why you get missing when you try to compute sd by(id
date). If you are trying to compute the intra-day volatility for each id you
need intra-day data (by the minute or tick data), in that case, for each
date, for each id you should have several returns. Your data apprears to be
daily data (Unless id stands some timeid). So you need to think again about
what you are trying to do.
Re you statement "but I don't know how to insert also the date, so that I
can compute the intraday volatility"
I suppose that refers to the missing dates in your example (the date is
missing for id 2 and 3).You can see more here
http://www.stata.com/support/faqs/data/missing.html
You can insert the dates by
replace date= date[_n-1] if date>= .
You can see this using Martin's example which I modified
*******
clear*
input str10 Date return byte id
"02/01/2009" .0003247 1
"" .005724 2
"" .0001587 3
"03/01/2009" .0000997 1
"" .0002494 2
"" .000071 3
"05/01/2009" .0001245 1
"" .00015879 2
"" .0003546 3
end
Compress
gen date=date(Date, "DMY")
format date %tdMonth_DD,_CCYY
list
replace date= date[_n-1] if date>= .
list
*************
Hope this helps
rajesh
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Nick Cox
Sent: 07 December 2009 18:32
To: [email protected]
Subject: RE: st: RE: Intraday volatility
Your problem was Martin's point, just made. If you have one measurement for
each combination of day and id, there is no variability to measure. In
addition, Stata uses n - 1 within the formula for s.d. so the result is
missing. So, no surprise there.
Nick
[email protected]
Beatrice Crozza
yes, volatility means standard deviation.
I already tried what you suggested me but I received all missing values.
Why?
2009/12/7 Nick Cox <[email protected]>:
> If volatility means here standard deviation, as I infer, then
>
> egen st = sd(return), by(id date)
>
> may be what you want.
>
> Nick
> [email protected]
>
> these are my data:
>
> Date return id
> 02/01/2009 .0003247 1
> .005724 2
> .0001587 3
>
> 03/01/2009 .0000997 1
> .0002494 2
> .000071 3
>
> 05/01/2009 .0001245 1
> .00015879 2
> .0003546 3
>
> I would like to compute the intraday volatility, i.e. the volatility
> for each day divided by the id.
> I typed:
> egen st=sd(return), by (id)
>
> but I don't know how to insert also the date, so that I can compute
> the intraday volatility.
*
* 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/
*
* 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/
*
* 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/
