Return to Answer

I could easily add some numerical refinements to prevent subtractive cancelation when $p$ is close to 1 by defining

w <- linkderiv <- plogis(eta) * plogis(eta, lower.tail=FALSE),

but the simple code above still handles the example well enough.

I could easily refine the code to prevent subtractive cancelation when p is close to 1 by defining

w <- linkderiv <- plogis(eta) * plogis(eta, lower.tail=FALSE)

but the more readable code above already handles the example well enough.

I could easily add some numerical refinements to prevent subtractive cancelation when $p$ is close to 1 by defining

w <- linkderiv <- plogis(eta) * plogis(eta, lower.tail=FALSE),

but the simple code above still handles the example well enough.

Example with direct code implementation of glm algorithm

p <- rep(0.5,n)

for (i in 1:10) {
  w <- p*(1-p)
  linkderiv <- p*(1-p)
  z <- (y-p)/linkderiv + qlogis(p)
  fit <- lm.wfit(X,z,w)
  p <- plogis(fit$fitted.value)
  cat(p,"\n")
}

Example with ``manual'' calculations

p <- rep(0.5,n)
eta <- qlogis(p)

for (i in 1:10) {
  w <- p*(1-p)
  linkderiv <- p*(1-p)
  z <- (y-p)/linkderiv + eta
  fit <- lm.wfit(X,z,w)
  eta <- fit$fitted.value
  p <- plogis(eta)
  cat(p,"\n")
}