If the effects are fixed, the models are essentially regression models with dummy variables that correspond to the specified effects. For fixedeffects models, ordinary least squares (OLS) estimation is equivalent to best linear unbiased estimation.
The output from TSCSREG is identical to what one would obtain from creating dummy variables to represent the crosssectional and time (fixed) effects. The output is presented in this manner to facilitate comparisons to the least squares dummy variables estimator (LSDV). As such, the inclusion of a intercept term implies that one dummy variable must be dropped. The actual estimation of the fixedeffects models is not LSDV. LSDV is much too cumbersome to implement. Instead, TSCSREG operates in a two step fashion. In the first step, the following occurs:
Oneway fixedeffects model: In the oneway fixedeffects model, the data is transformed by removing the crosssectional means from the dependent and independent variables. The following is true:


Twoway fixedeffects model: In the twoway fixedeffects model, the data is transformed by removing the crosssectional and time means and adding back the overall means:


where the symbols:
and are the dependent variable (a scalar) and the explanatory variables (a vector whose columns are the explanatory variables not including a constant), respectively
and are cross section means
and are time means
and are the overall means
The second step consists of running OLS on the properly demeaned series, provided that the data are balanced. The unbalanced case is slightly more difficult, because the structure of the missing data must be retained. For this case, PROC TSCSREG uses a slight specialization on Wansbeek and Kapteyn.
The other alternative is to assume that the effects are random. In the oneway case, , , and for , and is uncorrelated with for all and . In the twoway case, in addition to all of the preceding, , , and for , and the are uncorrelated with the and the for all and . Thus, the model is a variance components model, with the variance components , , and , to be estimated. A crucial implication of such a specification is that the effects are independent of the regressors. For randomeffects models, the estimation method is an estimated generalized least squares (EGLS) procedure that involves estimating the variance components in the first stage and using the estimated variance covariance matrix thus obtained to apply generalized least squares (GLS) to the data.