Say I have the following model:

$$y_{it} = \gamma_i + \delta {T}_{it} + \zeta Z_{i(k)} + \epsilon_{it}$$

where $y$ is some outcome for household $i$ in month $t$. $\gamma_i$ denotes household fixed effects. $T_{it}$ is treatment dummy. Say I have 240 months worth of data. The variable $Z$ represents a vector of time-varying covariates, but they vary across years.


I want to be very explicit about the variation, but I also don't want to confuse any readers. Is writing out $Z_{i(k)}$ appropriate, where $k$ is the subscript denoting the yearly variation? I figured this notation is a bit weird since I already stated that the time frequency was months, not years.

This question is about scientific reporting, so I believe it's apt for this community. I'm most concerned about the clarity of the model, in particular the subscripts.



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.