作者: Wei Bocheng , Tang Niansheng , Wang Xueren
DOI: 10.1007/S11766-000-0024-5
关键词: Quasi-likelihood 、 Mathematics 、 Applied mathematics 、 Nonlinear system 、 Inner product space 、 Nonlinear regression 、 Exponential family 、 Inference 、 Mathematical optimization 、 Euclidean geometry 、 Variance (accounting)
摘要: A modified Bates and Watts geometric framework is proposed for quasi-likelihood nonlinear models in Euclidean inner product space. Based on the framework, some asymptotic inference terms of curvatures studied. Several previous results regression exponential family etc. are extended to models.