Integrated Likelihood Approach to Inference with Many Instruments

I analyze a Gaussian linear instrumental variables model with a single endogenous regressor in which the number of instruments is large. I use an invariance property of the model and a Bernstein-von Mises type argument to construct an integrated likelihood which by design yields inference procedures that are valid under many instrument asymptotics and are asymptotically optimal under rotation invariance. I establish that this integrated likelihood coincides with the random-effects likelihood of Chamberlain and Imbens (2004), and that the maximum likelihood estimator of the parameter of interest coincides with the limited information maximum likelihood (liml) estimator. Building on these results, I then relax the basic setup along two dimensions. First, I drop the assumption of Gaussianity. In this case, liml is no longer optimal, and I derive a new, more efficient estimator based on a minimum distance objective function that imposes a rank restriction on the matrix of second moments of the reduced-form coefficients. Second, I consider minimum distance estimation without imposing the rank restriction and I show that the resulting estimator corresponds to a version of the bias-corrected two-stage least squares estimator.