“…While the info‐metric perspective is intuitively appealing, it is often more convenient for the purposes of developing the statistical theory to take the GEL perspective, which is essentially the dual of the info‐metric approach, although it was derived by Smith () via a different route (for further discussion, see Newey and Smith (); Kitamura (); Parente & Smith, ). Smith () defines the GEL estimator of to bewhere ρ ( a ) is a continuous, twice differentiable and concave function on its domain , an open interval containing 0, , and λ is an auxiliary parameter vector restricted so that, with probability approaching 1, , for all and t = 1,…, T .…”