Re: st: Missing data question.

[Maarten Buis <maartenlbuis@gmail.com>]

Others have already pointed to -mi-. One additional word of warning:
Imputation is there for the situation that the values exist but for
some reason have not been observed. It cannot help in the situation
where the value was not observed because it does not exist, e.g. the
stock of a firm that no longer exists.

-- Maarten

On Sat, Feb 9, 2013 at 2:12 PM, Benjamin Hong <benjamin1459@gmail.com> wrote:
> Dear all,
>
> I am just starting to learn STATA. I am struggling with missing datas
> in my dataset.(82 stocks, historical monthly stock price data for
> 20years)
> I need to take the average of the stock's return for as many year as I
> can, where there are so many missing data as the industry is quite
> volatile sector.
> I decided to use 10years out of 20 years, as I deem appropriate,
> however there are still so many missing data and I dont want to simply
> exlcude them.
> I heard that there are some techinic called "imputation".
> Could you let me know how to employ this function in STATA?
>
> Many thanks.
>
> Ben
>
>
> ******************************************
> Benjamin (Wonki) Hong
> Certified Financial Risk Manager
> MSc Finance, Edinburgh University
> Phone: +44(0)752-121-9910
> E-mail: benjamin1459@gmail.com
> *
> *   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/



-- 
---------------------------------
Maarten L. Buis
WZB
Reichpietschufer 50
10785 Berlin
Germany

http://www.maartenbuis.nl
---------------------------------
*
*   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/