Exponential Family
Suppose Y1 , , Yn are independent random
variables.
Let f (yi ; i , ) be PMF or PDF of Yi , where
is a scale parameter.
If we can write
[ y b()
f (yi ; i , ) = exp
+ c(y, )],
a(
Overdispersion
For binomial or Poisson distribution, the variance is determined if the expected value is known.
Sometimes in real application, we observe a deviance of a Pearson goodness of t much lar
Survival Analysis
Stat 526
January 6, 2015
1
Functions of Survival Time
Let T be the survival time for a subject. Then P [T < 0] = 0 and T is a continuous random
variable. The Survival function is den
ADVANCED STATISTICAL METHODOLOGY (STAT 526)
MIDTERM EXAM (SMTH 118)
8:00-10:00PM, MONDAY, MARCH 09, 2015
There are totally 32 points in the exam. The students with score higher than or equal to 30
poi
#
# Random Effect
#
pulp <- read.table("c:\tonglinzhang\stat526\pulp.txt",h=T)
pulp
#
# This is onw-way model. The first variable is response and
# the second one is the covariate variable.
#
op <- op