Open AccessMicrocomputer-Based Nonlinear Regression Analysis of Ligand-Binding Data: Application of Akaike's Information Criterion
Author(s) -
Keita Kamikubo,
Hiroshi Murase,
Masanori Murayama,
Kiyoshi Miura
Publication year - 1986
Publication title -
japanese journal of pharmacology/japanese journal of pharmacology
Language(s) - English
Resource type - Journals
eISSN - 1347-3506
pISSN - 0021-5198
DOI - 10.1254/jjp.40.342
Subject(s) - akaike information criterion , bayesian information criterion , nonlinear regression , statistics , mathematics , linear regression , microcomputer , regression analysis , computer science , telecommunications , chip
Akaike's information criterion (AIC) (Akaike, H., IEEE Trans. Automat. Contr. AC-19, 716-723 (1974)) was applied to estimate statistically the number of classes of binding sites from ligand-binding data. Several sets of data were analyzed by both the AIC method and the F-test method. Good agreement was obtained between results from both methods. The present results suggest that the AIC method can be a good alternative to the F-test to estimate the number of classes of sites.