A Test for Global Maximum Academic Article uri icon

abstract

  • We give simple necessary and sufficient conditions for consistency and asymptotic optimality of a root to the likelihood equation. Based on the results, a large-sample test is proposed for detecting whether a given root is consistent and asymptotically efficient, a property often possessed by the global maximizer of the likelihood function. A number of examples, and the connection between the proposed test and the test of White for model misspecification, are discussed. Monte Carlo studies show that the test performs quite well when the sample size is large but may suffer the problem of overrejection with relatively small samples. 1999 Taylor & Francis Group, LLC.

published proceedings

  • Journal of the American Statistical Association

altmetric score

  • 1.25

author list (cited authors)

  • Gan, L. i., & Jiang, J.

citation count

  • 29

complete list of authors

  • Gan, Li||Jiang, Jiming

publication date

  • January 1999