st: the best way to elaborate the data that will be imported in STATA

["nicolescu i. (in3g10)" <in3g10@soton.ac.uk>]

Dear Stata users,

For my BSc Economics dissertation- Empirical Methodology, I'm considering a dynamic panel data and as an estimation method the first-difference and system GMM.

I have a panel data from 1985 to 2010 for 23 countries and I want to average my data over a 5 year period for the variables y, x1, x2. Then I want to regress average y for 5 year intervals on the lagged y (which is the initial value in the first year of the 5-year intervals) and the average x1, x2 and x3 over 5 year periods (the data for x3 was only available as average over 5 years).

The dependent variable y is the change in the logarithm of real GDP per worker at five-year intervals, and the lagged variable on the right-hand side of the equation is the initial level of income starting in 1990, 1995, 2000, 2005 and ending in 2010. The other explanatory variables are logarithms of savings, population growth and human capital.

I tried to calculate these averages in Excel and then do the regression in STATA but I didn’t know how to work with y_t (the dependent variable) as an average over 5-year intervals and y_t-1(lagged variable) as the initial value in the first year of the 5-year intervals). If I use the average y variable in STATA, its lagged value will also be an average and not an initial value as required.

Is there a way to do all this steps in STATA?
Within this context, which is the best way to elaborate the data that will be imported in STATA?


Many thanks,

Ioana

*
*   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/