Download presentation
Presentation is loading. Please wait.
1
4.6 Fitting generalized linear models
Newton-Raphson method Fisher scoring method
2
4.6.1 Newton-Raphson method
8
SAS code /*Newton-Raphson*/ proc IML; y=20; n=100; u=1:10; H=1:10; b=1:10; b[1]=0.1; do i=1 to 10; H[i+1]=-y/b[i]**2-(n-y)/(1-b[i])**2; u[i+1]=(y-n*b[i])/(b[i]*(1-b[i])); b[i+1]=b[i]-1/H[i+1] *u[i+1]; end; print b;
9
4.6.2 Fisher scoring method
13
4.7 Quasi-likelihood and generalized linear models
16
4.7.2 Overdispersion for Poisson GLMs and quasi-likelihood
27
4.7.4 Teratology overdispersion example
31
SAS code data moore; input litter group n y @@; datalines;
… ; proc genmod; class group; model y/n = group / dist = bin link = identity noint; estimate ‘pi1- pi2 ’ group ; model y/n = group / dist = bin link = identity noint scale = pearson;
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.