ABSTRACT
Panel data covered in this chapter refer to data sets consisting of cross-sectional observations over time, or pooled cross section and time series data. They have two dimensions, one for time andone for the cross-section entity.Wehavebeen familiar with the time dimension already, using a subscript t to the variable to stand for the time dimension, with t = 1,2, . . . T for T observations at the T time points. For the cross-sectional data, the entity can be individuals, firms, regions or countries, as introduced in the two preceding chapters. The subscript n to the variable is usually adopted to represent the cross-section dimension, with n = 1,2, . . . N for N observations for N different entities, e.g., N firms. There can be other forms of panels, as long as there are two dimensions for the observations; but only panel data with a time dimension and a cross-section dimension are covered in this chapter.
