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: Missing Values
From
Nick Cox <[email protected]>
To
"[email protected]" <[email protected]>
Subject
Re: st: Missing Values
Date
Tue, 7 Jan 2014 18:22:56 +0000
That's not what you said, but it makes more sense. Here is some technique:
First, you show no data, so we need a sandpit to play in:
webuse grunfeld, clear
set seed 2803
replace invest = . if runiform() < 0.7
Download -tsspell- from SSC and then identify spells of missing values:
tsspell , c(missing(invest))
The length of each spell is an easy calculation
egen max = max(_seq), by(company _spell)
Then any interpolation is made conditional:
by company: ipolate invest year if max <= 5, gen(invest2)
For explanation of the _principles_ of identifying spells, see
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
http://www.stata-journal.com/sjpdf.html?articlenum=dm0029
Nick
[email protected]
On 7 January 2014 17:37, Sadia Khalid <[email protected]> wrote:
> @Nick Cox
>
> I only want to fill in the missing values if the no of missing values
> are equal to or less than 5. if 5 or more values are missing than do
> not fill in the missing values.
>
> On 7 January 2014 22:31, Nick Cox <[email protected]> wrote:
>> <>
>>
>> So 5 is OK for interpolation, but 4 or 6 isn't? Sounds bizarre.
>>
>> Nick
>> [email protected]
>>
>>
>> On 7 January 2014 17:22, Sadia Khalid <[email protected]> wrote:
>>>
>>> I have read about your code for filling the in between missing values
>>> at http://www.stata.com/statalist/archive/2003-05/msg00247.html
>>>
>>> I want the code that fill the missing values only if 5 inbetween
>>> values are missing.
*
* 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/