作者: David R. Anderson , Kenneth P. Burnham
DOI: 10.1080/00063659909477253
关键词: Econometrics 、 Inference 、 Mathematics 、 Set (abstract data type) 、 A priori and a posteriori 、 Statistical hypothesis testing 、 Ranking 、 Data dredging 、 Model selection 、 Data mining 、 Estimator
摘要: A general, consistent strategy for data analysis is outlined, based on information and likelihood theory. priori considerations lead to the definition of a set candidate models, simple criteria are useful in ranking calibrating models estimates (relative) Kullback-Leibler information, inference can be either best model or weighted average several models. Model selection uncertainty quantified should incorporated into estimators precision. Some comments offered statistical hypothesis testing dredging.