Re: st: Missing observations

[Csaba <csaba.kertai@hotmail.co.uk>]

Thank you David! Please see my previous message to Nick. My real problem is not missing values. I have to test the mean/median/25th percentile/75th percentile/90th percentile/'% of positive values' differences using ttests as well as bootstrapping and I judt cannot get my head round this. 

Thank you.

On 20 Jun 2013, at 13:20, David Hoaglin <dchoaglin@gmail.com> wrote:

> Simply dropping missing values or, more commonly, dropping
> observations in which the value of any variable is missing requires
> careful consideration of the reasons that are responsible for those
> values' being missing.  In the mechanism underlying the "missingness"
> does not satisfy certain assumptions, using only the "complete cases"
> or the available data can lead to serious bias.  The topic of missing
> data has a large literature, including the book by Little and Rubin
> (2001).
> 
> David Hoaglin
> 
> Little RJA, Rubin DB (2001).  Statistical Analysis with Missing Data,
> 2nd ed.  Wiley.
> 
> On Thu, Jun 20, 2013 at 6:17 AM, Csaba Kertai
> <csaba.kertai@hotmail.co.uk> wrote:
>> Dear All,
>> 
>> I need a bit of help with dropping missing observations. If I use 'drop if missing(var)' or drop if 'var'==. etc. many other observations are dropped as well. More precisely, var1 has 1125 observations and var2 has 169 observations. I want to drop missing observations for var2 but if I use drop if var2==. then this will keep only 169 observations for each variable. I only want to drop values that are missing.
>> 
>> Any help is greatly appreciated.
> 
> *
> *   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/