广义线性模型 a1.pdfVIP

Appendix A Review of Likelihood Theory This is a brief summary of some of the key results we need from likelihood theory. A.1 Maximum Likelihood Estimation Let Y , . . . , Y be n independent random variables (r.v.’s) with probability 1 n density functions (pdf) f (y ; θ) depending on a vector-valued parameter θ. i i A.1.1 The Log-likelihood Function The joint density of n independent observations y = (y , . . . , y ) is 1 n