This paper provides a selective survey of the panel macroeconometric techniques that
focus on controlling the impact of “unobserved heterogeneity” across individuals and over
time to obtain valid inference for “structures” that are common across individuals and
overtime. We consider issues of (i) estimating vector autoregressive models; (ii) testing
of unit root or cointegration;(iii) statistical inference for dynamics imultaneous equations
models;(iv) policy evaluation; and (v)aggregation and prediction.