STABILITY AND UNIQUENESS OF p-VALUES FOR LIKELIHOOD-BASED INFERENCE
THOMAS J. DICICCIO, TODD A. KUFFNER, G. ALASTAIR YOUNG, AND RUSSELL ZARETZKI
ABSTRACT. Likelihood-basedmethods of statistical inference provide a useful general methodology that is
appealing, as a straightforward asymptotic theory can be applied for their implementation. It is important to
assess the relationships between different likelihood-based inferential procedures in terms of accuracy and
adherence to key principles of statistical inference, in particular those relating to conditioning on relevant
ancillary statistics. An analysis is given of the stability properties of a general class of likelihood-based
statistics, including those derived from forms of adjusted profile likelihood, and comparisons are made
between inferences derived from different statistics. In particular, we derive a set of sufficient conditions
for agreement to Op(n−1), in terms of the sample size n, of inferences, specifically p-values, derived from
different asymptotically standard normal pivots. Our analysis includes inference problems concerning a
scalar or vector interest parameter, in the presence of a nuisance parameter.
STABILITY AND UNIQUENESS OF p-VALUES FOR LIKELIHOOD-BASED INFERENCETHOMAS J. DICICCIO, TODD A. KUFFNER, G. ALASTAIR YOUNG, AND RUSSELL ZARETZKIABSTRACT. Likelihood-basedmethods of statistical inference provide a useful general methodology that isappealing, as a straightforward asymptotic theory can be applied for their implementation. It is important toassess the relationships between different likelihood-based inferential procedures in terms of accuracy andadherence to key principles of statistical inference, in particular those relating to conditioning on relevantancillary statistics. An analysis is given of the stability properties of a general class of likelihood-basedstatistics, including those derived from forms of adjusted profile likelihood, and comparisons are madebetween inferences derived from different statistics. In particular, we derive a set of sufficient conditionsfor agreement to Op(n−1), in terms of the sample size n, of inferences, specifically p-values, derived fromdifferent asymptotically standard normal pivots. Our analysis includes inference problems concerning ascalar or vector interest parameter, in the presence of a nuisance parameter.
การแปล กรุณารอสักครู่..
