[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: unbalanced panel to balanced panel
I am using Stata/SE 8.2 for my research and layman in
stata programming. Much appreciate if you could kindly
comment or direct me on the following issues:
For your information, I would like to inform you that
I have observations of 212 banks over 1997 to 2004.
The panel is unbalanced. The observations are in
lead/lag format, i.e., dependent variable is at time t
and independent variables are at t-1.
1. Creating a balanced panel (not by filling missing
values but by eliminating the corresponding rows). I
need a balanced panel to run xtgls.
2. Converting the lead/lag unbalanced panel to
unbalanced panel of contemporaneous observations of
all variables. I can understand that I will be loosing
one year observations.
3. Test procedures: Ranking the observations according
to variable X for each year. Then testing the
difference in mean between observations in the top
quartile and bottom quartile for each year for
variables y1 and y2.
4. Creating a new variable in panel data: which is
y = (y(t) - y(t-1))/y(t-1)
My apologize for being very layman in my questions and
detail discussion. I can do the stuffs manually in
excel but I am sure there must be some code/macros to
do the stuffs easily in stata!
Thank you in advance for any of your comments or
Dept. of Acc. & Finance,
T: 61 3 99031259
H: 61 3 95631338
F: 61 3 99032442
N.B.: I went through the FAQs and also statalists
archives but failed to an insights.
Do you Yahoo!?
Everyone is raving about the all-new Yahoo! Mail beta.
* For searches and help try: