|
HOME
LECTURE MATERIALS
HOMEWORK and PROJECTS
DATA SETS
MUSC Division of Biostatistics
and Epidemiology Home Page
|
|
|
Welcome to the 2010 homepage for
Biometry 726
Instructor: Elizabeth G. Hill, Ph.D.
Office: Hollings Cancer Center, 118D
Email: hille@musc.edu
Phone: 876-1115
Fax: 792-4233
Office Hours: Tuesday, 3 – 4pm and Friday, 1 – 2pm
Lecture: T/Th 1:30-3:00pm, Cannon Place Room 301
Course website: http://people.musc.edu/~hille/BMTRY726/
Prerequisites: Biometry 700, 701,
706 and 707
Textbook: Applied Multivariate
Statistical Analysis, 6th Edition. Richard A. Johnson and Dean W.
Wichern, 2008.
Evaluation
- Class Participation
– 10%
- Homework – 30%
- Project 1 – 30%
- Project 2 – 30%
Important Dates
- Tuesday, September 7th
– Last day to drop or add classes
- Tuesday, November 2nd
– No class – election day
- Thursday, November 25th
– No class – Thanksgiving
- Thursday, December 9th
– Last class
Class Participation
All students are expected to attend class regularly. As a courtesy to
both your instructor and your fellow classmates, please make every effort to
be prompt, as class will begin at the scheduled time. The course covers
a tremendous amount of material and all classes will be used for lecture or
lab activities. Ten percent of the course grade is based on your
regular participation and all students are awarded ten points at the start of
the semester. Some absences, however, are unavoidable. In an
effort to accommodate our busy professional and personal lives, all students
can miss up to two classes without penalty. Note that an absence is
defined as missing more than 15 minutes of any scheduled lecture.
One point is deducted from the class participation grade for each subsequent
absence. For example, if you miss four lectures then your class
participation grade is an 80% (two absences with
impunity, with the two additional absences resulting in an 8/10 for
participation).
Special circumstances (e.g. birth or death in
family, family illness) will be dealt with on an individual
basis.
Homework
Homework should be submitted
electronically. I prefer
LaTeX documents, but you may use Word if you prefer. However, if you wish to hand-write
your homework and then send a scanned electronic copy, please be sure your handwriting is legible. Work that is illegible will not be
graded. Homework turned in one
day late will receive a 25% reduction, two days late will receive a 50%
reduction, and homework more than two days late will not be accepted.
Projects
There
will be two projects this semester.
These are data analysis projects using methods discussed in class for
which you are required to write a paper.
The paper should be structured like a scientific manuscript with: introduction, materials and methods,
results, and discussion sections.
Developing good communication skills is an important part of your training
as a biostatistician, and communicating statistics is an essential component
of a statistician’s job.
Therefore, you will be graded not only on the appropriateness of the
statistical methods and your ability to correctly interpret results, but also
on your ability to communicate effectively in written format. The policy for late projects is the
same as that for late homework.
Computing
We will use R and SAS version 9.2.
Course Topics
- Multivariate data
- Matrix algebra review
- Random Vectors
- Multivariate normal
distribution
- One-Sample, Hotellings
T
- One-Sample Confidence
Regions, Intervals
- Maximum Likelihood for
Multiv. Normal
- Missing Data in
Multiv. Normal
- Two Sample Tests
- One-way MANOVA
- Two-way MANOVA
- Multivariate multiple
linear regression
- Profile Analysis
- Studies with Clustered
Continuous Outcomes
- Random Effects Models
for Clustered Data
- Mixed Models for
Clustered Data
- Generalized Least
Squares, Maximum Likelihood
- Longitudinal Models
for Continuous Outcomes
- Robustness of
Generalized Least Squares
- Studies with Clustered
Binary Outcomes
- Logistic Regression,
extension to Clusters
- Models-Clustered and
Longitudinal Binary Data
- Generalized Estimating
Equations
- Principal component
analysis
- Canonical Correlation
- Factor Analysis
- Discriminant function
analysis/Classification
- Cluster Analysis
|
|
|
|
