Let y have a geometric distribution with probability mass function f(y;p)=(1-p)py y=0,1,... The deviance residual for observation i is given by sign(yi - wi) di where di is the deviance associated with observation i, and is written as a function of the response variable y; and the fitted value u; while sign(.) is the sign function defined in the lecture notes. Which of the following is the correct expression for di when the generalised linear model is geometric? Notes: (i) Precisely one answer below is correct and the others are incorrect. (ii) An incorrect answer scores zero while the correct answer scores full marks for the question. Select one: O a. d,2 = 2ly; log (yi/wj)-(yi+1)log((y;+1)/(uj+1))] O b. d 2 =2 y; log(yi /Li) O c. d 2=2[y; log(y;/; )- yi + mi] O d. d;2 = 2 ( yi - Hi) 2 / (Hit Hi? )