I have a question regarding an answer of another question posted here.
My dataset seems comparable and has different policy treatment timings for different firms. The answer outlines how to construct the $\text{Policy}_{it}$ dummy variable (where $\text{Treated}_{it}$ and $\text{Post}_{it}$ equal 1), for different treatment timings with a difference-in-differences estimator on a panel data set.
In his example table, firm 1 has $\text{Post}_{it}$ (an indicator for the post treatment period) dummy values, which are equal to 1 for time periods 3 and 4. For completeness, a copy of his sample:
$$ \begin{array}{ccccc} \text{firm} & \text{time} & \text{treated} & \text{post} & \text{policy} \\ \hline 1 & 1 & 0 & 0 & 0 \\ 1 & 2 & 0 & 0 & 0 \\ 1 & 3 & 0 & 1 & 0 \\ 1 & 4 & 0 & 1 & 0 \\ \hline 2 & 1 & 1 & 0 & 0 \\ 2 & 2 & 1 & 0 & 0 \\ 2 & 3 & 1 & 1 & 1 \\ 2 & 4 & 1 & 1 & 1 \\ \hline 3 & 1 & 1 & 0 & 0 \\ 3 & 2 & 1 & 0 & 0 \\ 3 & 3 & 1 & 0 & 0 \\ 3 & 4 & 1 & 1 & 1 \\ \end{array} $$
I am confused as how it could be possible to have a $\text{Post}$ dummy equalling 1 for a non treated firm (firm 1), as the dataset contains different treatment timings (or no treatment at all) for different firms (ie. it is on a country basis). IMO this implies $\text{Policy}$ is the same variable as $\text{Post}$. Does DiD with different treatment timings require that for all different treatment timings there is a non treated (control) group?
I am not that familiar with stats, so if the wrong question is asked, that could very well be possible. Any clarification would be great.
