PSTAT 175:
Proportional Hazards Models
October 25, 2016
Reading
Survival Analysis: A Self-Learning Text Kleinbaum and Klein. Chapter 3 pp. 100108.
Likelihood Ratio test
Whenever we have an MLE, we can use it to form a Likelihood Ratio Test.
LRT: The nul

PSTAT 175:
Assignment # 1
Due Friday October 17, 2014
1. The Weibull distribution has a survivor function of Pcfw_T > t = exp [(t) ].
(a) Prove that the density function is
f (t) = t1 exp [(t) ]
for t > 0.
(b) Show that the hazard function for t > 0 is
h(

PSTAT 175:
Assignment #3
due November 18, 2014
1. We have 2n subjects in an experiment. The failure time for each subject follows an exponential
distribution. Of these subjects, n subjects have hazard rate A and are in Group A, and the other n
subjects ha

PSTAT 175:
Practice Final Question Solutions
Final Exam: Wed, December 17 12:003:00
Practice Questions
1. A multi-center trial of a new drug protocol decided to perform the analysis stratifying on the clinics.
The experimenters measured the time until rel

PSTAT 175:
Assignment #2
due October 31, 2014
This assignment is due at 1:00PM on Friday. You can either turn in your assignment online, or you can drop
your paper at Prof. Carters office in 5507 South Hall.
1. Taking the heart transplant data we looked a

PSTAT 175:
Practice Final Questions
Final Exam: Wed, December 17 12:003:00
The final exam will be a closed-book three-hour exam. You will need
A blue book to write your answers
A calculator (not a laptop or smartphone)
One page (one side of an 8.5 by 1

PSTAT 175:
R Introduction
Due October 9, 2014
Please work through these questions, and submit a report via the Gauchospace page. Your report should
include R input and output as well answers to the questions and relevant graphs.
1. Create a vector x with

PSTAT 175:
Lab D: Proportional Hazards Model fitting and checking
Due November 25, 2014
Please submit your report on Gauchospace by the end of the day on Tuesday.
In the survival package, there is a data set called mgus which gives the result of a study o

PSTAT 175:
Lab C: Comparing Samples
Due November 7, 2014
1. The rats data is available in the survival package and on GauchoSpace. The rats were given carcinogenic medications and the time until tumor development was measured. The treatment group in
the s

PSTAT 175:
Nonparametric Survivor Function Estimates
Due October 24, 2014
Please work through these questions, and submit a report via the Gauchospace page. Your report should
include R input and output as well answers to the questions and relevant graphs

Survival Data
Drew Carter
September 22, 2016
Black Duck
Figure 1: BlackDuck
Data Table
Histogram
library(survival)
ducks <- read.table("C:/Users/carter/Desktop/175/Data/Modelling Survival Data/Survival of black ducks.da
header = TRUE, quote = "\")
hist(du

PSTAT 175:
Hazard Functions
September 29, 2016
1. General Nonparametric Estimation for discrete models
2. Hazard Function Interpretation
3. Approximating Continuous models with intervals (life tables)
Changing Hazard Rate
Define a new experiment where 1

PSTAT 175:
Information and Class Policies
Instructor
Drew Carter
Office hours: TBA
Office: 5507 South Hall
Email: carter@pstat.ucsb.edu
TA
Sergio Rodriguez (srodriguez@pstat.ucsb.edu)
Changwei Xu (cxu@pstat.ucsb.edu)
Office Hours: TBA
September 22, 2016
G

PSTAT 175:
Modeling Survival Data
September 27, 2016
Write the course number in email correspondence.
DSP is looking for a Note Taker.
Binomial Model
n is the number of independent trials. X = the number of successes. p is the probability of success.