PH 627-Alcaraz-s11.pdf - Graduate School of Public Health - San ...

SAN DIEGOSTATEUNIVERSITY
Graduate School of Public Health
Division of Epidemiology and Biostatistics
PH 627Advanced Statistical Methods in Public Health 3 units
Spring 2011
Section Day Time Location Schedule No.
1 Tues Thurs 9:30am – 10:45am HH 128 22293
2 Tues Thurs 11:00am – 12:15pm HH 128 22294
Instructor: John Alcaraz, Ph.D. Office location: Hardy Tower 231
Office phone: (619) 594-1342 Office hours: Tues Thurs 1:30pm – 3:30pm
E-mail:jalcaraz@mail.sdsu.edu
Prerequisites:
1) A grade of B or better in PH 602, and 2) concurrent enrollment in the SAS lab course or a good
working knowledge of SAS.
Required Texts:
– Kleinbaum, Kupper, Muller, Nizam: Applied Regression Analysis and Multivariable Methods,
4th edition.
– Slymen: “PH 627: Annotated SAS Output for Public Health” (Customized Materials).
Note: The annotated output should be brought to every class meeting.
Grading System*:
Homework: 15% 93 – 100 = A 73 – 77 = C
Midterm: 35% 90 – 93 = A– 70 – 73 = C–
Final Exam: 50% 87 – 90 = B+ 67 – 70 = D+
83 – 87 = B 63 – 67 = D
80 – 83 = B– 60 – 63 = D–
77 – 80 = C+ 0 – 60 = F
* Somehomework will require using SAS on the PC. Both the midterm and the final exam are
open book, open notes. The final exam is comprehensive.
Homework Dates (subject to change):
Date Assigned Date Due
Homework 1 Jan 25 Feb 1
Homework 2 Feb 1 Feb 8
Homework 3 Feb 8 Feb 15
Homework 4 Feb 15 Feb 22
Homework 5 Feb 22 Mar 1
Homework 6 Mar 8 Mar 15
Homework 7 Mar 15 Mar 22
Homework 8 Apr 5 Apr 12
Homework 9 Apr 12 Apr 19
Homework 10 Apr 19 Apr 26
Homework 11 Apr 26 May 3
- 1 -

Exam Dates and Times (subject to change):
Part 1 (in-class) Part 2 (in-class)
Section 1
Midterm Mar 22 (9:30am – 10:45am) Mar 24 (9:30am – 10:45am)
Final May 10 (9:30am – 10:45am) May 17 (8:00am – 10:00am)
Section 2
Midterm Mar 22 (11:00am – 12:15pm) Mar 24 (11:00am – 12:15pm)
Final May 10 (11:00am – 12:15pm) May 19 (10:30am – 12:30pm)
Academic Ethics:
SDSU has a strict code of ethical conduct which students are expected to follow.
Seehttp://csrr.sdsu.edu/conduct1.htmlfor details. In particular, cheating will not be tolerated. You
may not work together on the midterm or final exam, may not copy other students’ work, and
may not allow other students to copy your work. Anyone caught cheating will face disciplinary
action.
Attendance/Punctuality:
While attendance is not required except for exam dates, students are strongly encouraged to
attend every class meeting and to be punctual. On exam dates, the exam will start and end at
exactly the times listed above. Those who arrive late on exam dates will not be allowed to work
past the end time to complete their exams.
If you miss an exam because of severe circumstances (such as illness, injury, death in the family),
please contact me no later than one week after the exam to arrange a makeup test.
Students for whom an exam falls on a date of religious observance should contact me by the end
of the second week of classes to discuss alternative arrangements.
Students with Disabilities:
Students with disabilities should discuss with me privately any specific accommodations for
which they have received authorization. Authorization may be obtained by contacting Student
Disability Services at 619-594-6473 (Calpulli Center, Suite 3101). Please obtain authorization
before making an appointment to see me.
- 2 -

Learning Objectives:
Upon completion of this course the student will learn the appropriate use of advanced statistical
methods for the analysis of data with continuous and binary responses, and the analysis of
survival data. Emphasis will be placed on regression techniques where multivariable adjustment
and the simultaneous evaluation of risk factors are required.
Specific objectives are:
1) To describe the basic mathematical models used in multiple linear regression, analysis of
variance, logistic regression, and survival analysis. This includes a description of model
assumptions, parametric estimation, confidence intervals, and hypothesis testing. Although this
course does not require the use of calculus, some lectures will outline the underlying mathematics
required to derive important results.
2) To choose the appropriate models in solving specific public health problems, and to be aware
of their strengths and limitations.
3) To interpret correctly the results from fitting these models to data, and to write appropriate
summaries for theses and reports.
4) To acquire the basic technical skills needed to analyze data using these methods. This will be
accomplished through examples of SAS output discussed in class and the SAS lab course.
These objectives should contribute to your ability to critically review the public health and
epidemiologic literature, and to carry out statistical analyses independently for your thesis and
later professional work.
Note: It is assumed that students know the material in PH602 including simple linear regression
and one-way ANOVA. If necessary, review the relevant portions of your PH 602 texts.
- 3 -

Course Outline for PH 627 *
Approx #
Topic Sem Hrs. Book Chapters
Regression: Continuous response
Displaying results in ANOVA table 1 7
Multiple regression 4 8 & 9
Multiple and partial correlation 2 10
Confounding and interaction 1 11
Dummy variables 2 12
Analysis of covariance 2 13
Analysis of variance
One-way 1 17
Random vs fixed effects 1 17
Multiple comparisons 1 17
Two-way 5
One observation per cell 18
> 1 observation per cell
Equal cells 19
Unequal cells 20
Regression: Binary response 22
Introduction to logistic regression 2
Adjusted odds ratio 1
Maximum likelihood estimation 1
Confidence intervals & hypothesis testing 2
Modeling issues 2
Analysis of survival data **
Concepts & examples 1
Functions of survival time 1
Estimation: Product-limit estimate 1
Life tables 1
Two-sample problem: Log-rank & generalized Wilcoxon tests 2
Regression- Cox proportional hazards model
Concepts 2
Estimation & hypothesis testing 3
Modeling issues 3
* Lecture notes for all topics will be available on Blackboard.
** Readings for survival analysis will be available on Blackboard.
- 4 -