To obtain consistency and asymptotic normality, a generalized method of moments (GMM) estimator typically is defined to be an approximate global minimizer of a GMM criterion function. To compute such an estimator, however, can be problematic because of the difficulty of global optimization. In consequence, practitioners usually ignore the problem and take the GMM estimator to be the result of a local optimization algorithm. This yields an estimator that is not necessarily consistent and asymptotically normal. The use of a local optimization algorithm also can run into the problem of instability due to flats or ridges in the criterion function, which makes it difficult to know when to stop the algorithm. To alleviate these problems of global and local optimization, we propose a stopping-rule (SR) procedure for computing GMM estimators. The SR procedure eliminates the need for global search with high probability. And, it provides an explicit SR for problems of stability that may arise with local optimization problems.

This paper introduces a conditional Kolmogorov test of model specification for parametric models with covariates (regressors). The test is an extension of the Kolmogorov test of goodness-of-fit for distribution functions. The test is shown to have power against 1/√n local alternatives and all fixed alternatives to the null hypothesis. A parametric bootstrap procedure is used to obtain critical values for the test.

The authors consider a family of rank tests based on the regression rank score process introduced by C. Gutenbrunner and J. Jureckova (1992) to test the unit root hypothesis in economic time series. In contrast to tests based on least-squares methods, the rank tests are asymptotically Gaussian under the null hypothesis, and have excellent power--particularly under innovation exhibiting heavy tails. These regression rank scores arise as a vector of solutions of the dual form of the linear program required to compute the regression quantile statistics of R. W. Koenker and G. Bassett (1978). For location model, they are simple ranks of the sample observations.