1. Dirty Pool
2. These are usually called fixed effects. I want to use a different term since terms such as fixed effects and random effects are also used as ways of estimating panel data models.
3. Panel Data and Unobservable Individual Effects
4. Efficient Estimation of Time-Invariant and Rarely Changing Variables in Finite Sample Panel Analyses with Unit Fixed Effects
5. Thus, one time-varying covariate, x, one TIV, z, and a separate unit effect were drawn (making varying assumptions about their correlation), the sum of the TIV and unit effects were then regressed on the TIV with a residual, r, calculated, and then the dependent variable was generated as the sum of the x, TIV, r, and an SE term uncorrelated with anything else. One thousand runs were analyzed.