Panel data and unobservable individual effects

摘要: Abstract An important purpose in pooling time-series and cross-section data is to control for individual-specific unobservable effects which may be correlated with other explanatory variables, e.g. latent ability measuring returns schooling earnings equations or managerial scale firm cost functions. Using instrumental variables the time-invariant characteristics of variable, we derive: 1. (1) a test presence this effect over-identifying restriction use; 2. (2) necessary sufficient conditions identification all parameters model; 3. (3) asymptotically efficient estimator under it differs from within-groups estimator. We calculate estimates wage equation Michigan income dynamics indicate substantial differences Balestra-Nerlove — particularly significantly higher estimate schooling.