st: RE: Converting unbalanced panel to balanced panel data

[Jan Bryla <JBR@finansraadet.dk>]

If you want to drop observations that are not present in all years of your study, generate an indicator for number of observations by pid, such as

Bys pid: gen nyear=[_N]
Keep if nyear==9 

Jan Bryla
The Danish Bankers Association


-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Muhammad Anees
Sent: 15. marts 2011 14:13
To: statalist@hsphsun2.harvard.edu
Subject: st: Converting unbalanced panel to balanced panel data

Hi!

I know I can apply most of the panel data estimations to balanced and
unbalanced panel dataset. Instead of this I would like you all to help
me out of this.

I have one very basic question in mind and came to no clue after
intensive research of the Stata help files and over the internet. I
have an unbalanced panel dataset and want to make it balanced. I would
present the xtdes results at the end of my email please bear my my
question first: How can I keep if all my id is present at all times so
that I come with atleast balanced panel?

Sorry for the very basic nature of my question.

xtdes

pid:  10016848, 10016872, ..., 1.794e+08	n	=	16368
year:  2001, 2002, ..., 2009	                        T	=	9
Delta(year) = 1 unit
Span(year)  = 9 periods
(pid*year uniquely identifies each observation)

Distribution of T_i:   min      5%     25%       50%	75%		95%     max
                               1        1         2           6	  9		9
           9

Freq.  Percent    Cum.   Pattern
---------------------------+-----------
5110     31.22   31.22   111111111
1450      8.86   40.08   ..1111111
1187      7.25   47.33   11.......
616      3.76   51.09   1........
486      2.97   54.06   ........1
423      2.58   56.65   .11111111
410      2.50   59.15   ......111
382      2.33   61.49   .......11
352      2.15   63.64   ..1......
5952     36.36  100.00  (other patterns)
---------------------------+-----------
16368    100.00           XXXXXXXXX



-- 
Muhammad Anees
MSc in Economics
*
*   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/