Fixed effects analysis

[Adeola Kolade]

Dear all,

I will please like to find out if i combine two cross sectional data to form a panel will my number of observations double
e.g cross sectional data 1=4000 and cross sectional data 2=4000 will panel be n=8000 or n=4000 if individuals are same in both data.

or if

cross sectional data 1=4000 and cross sectional data 2=3500 will my data be n=7500 or 4000 for same individuals

and if i have an unbalanced panel how do i make it balanced. I will really appreciate a reply.

[Andrew Musau]

I will please like to find out if i combine two cross sectional data to form a panel will my number of observations double
e.g cross sectional data 1=4000 and cross sectional data 2=4000 will panel be n=8000 or n=4000 if individuals are same in both data.

It depends what "n" is. Notationally, individuals are usually indexed by \(i\) and time by \(t\). So you have \(i=1, 2, \cdots, N\) and \(t=1, 2, \cdots, T\). That is, you have \(N\) individuals observed over \(T\) periods, and the total number of observations is \(NT\). This of course holds for a balanced panel. For an unbalanced panel, the number of observations is less than \(NT\).

and if i have an unbalanced panel how do i make it balanced. I will really appreciate a reply.

Look at the commands xtbalance and xtbalance2 from SSC.

[Adeola Kolade]

Many thanks Andrew.