Rating:
Date added: 27.4.2015
684 844
FB2PDFEPUB
This work covers the philosophy of model-based data analysis and provides an omnibus strategy for the analysis of empirical data. It introduces information theoretical approaches and focuses critical attention on a priori modelling and the selectionMoreThis work covers the philosophy of model-based data analysis and provides an omnibus strategy for the analysis of empirical data. It introduces information theoretical approaches and focuses critical attention on a priori modelling and the selection of a good approximating model that best represents the inference supported by the data. Kullback-Leibler information represents a fundamental quantity in science and is Hirotugu Akaikes basis for model selection. The maximized log-likelihood function can be bias-corrected to provide an estimate of expected, relative Kullback-Leibler information. This leads to Akaikes Information Criterion (AIC) and various extensions. The information theoretic approaches seek to provide a unified theory, an extension of likelihood theory. Model Selection And Inference: A Practical Information Theoretic Approach by Kenneth P. Burnham
