ENGR 274 - Generalized Linear Models (Winter 2004)
Expectations for derivatives of log-likelihoods
In order to obtain the mean and variance of a random variable with a distribution from the
exponential dispersion family (or the one-parameter exponential f
AMS 274 - Generalized Linear Models (Spring 2010)
Homework 1 (due Tuesday 13 April)
1. The list below comprises a number of distributions, including in each case, the support, parameter space, and density or probability mass function. Determine whether ea
AMS 274 Generalized Linear Models (Spring 2010)
Homework 5 (due by 12pm, Friday June 4)
Please email me a pdf le with your hwk; alternatively, you can slide your hwk under my oce
door. The hwk papers will be collected from my oce at noon on Friday June 4t
AMS 274 - Generalized Linear Models
Spring 2010
1. Denitions
Exponential dispersion family of distributions
Central to the development of generalized linear models (glms) is the exponential dispersion family
of distributions as it denes the random compone
AMS 274 Generalized Linear Models (Spring 2010)
Homework 2 (due Thursday 22 April)
1. Consider the special case of the Cauchy distribution, C(, 1), with scale parameter = 1, and
density function
f (y; ) =
1
,
(1 + (y )2 )
y R, R,
where is the median of th
AMS 274 Generalized Linear Models (Spring 2010)
Homework 4 (due Thursday 20 May)
1. The table below reports results from a developmental toxicity study involving ordinal categorical
outcomes. This study administered diethylene glycol dimethyl ether (an in
AMS 274 Generalized Linear Models (Spring 2010)
Homework 3 (due Tuesday 4 May)
1. Let yi , i = 1, ., n, be realizations of independent random variables Y i following gamma(i , )
distributions, with densities given by
f (yi ; i , ) =
1
(/i ) yi exp(yi /i )