EPIB 607 - Fall 2007
Principles of Inferential Statistics in Medicine

 Monday and Wednesday 11:05-12:25, and Mondays 1:35-2:25
Location: Purvis Hall 25
Office hours: Mondays 2:30-4:00am or by appointment

Erica E. M. Moodie
Purvis Hall room 38B
email: erica.moodie@mcgill.ca
Phone: 398-5520 (email preferable)
Prerequisite: Differentiable and integral calculus.
Objectives: The aim of this course is to provide students with basic principles of statistical inference applicable to clinical and epidemiologic  so that they can: (i) understand how statistical methods are used by others, (ii) apply statistical methods in their own research, and (iii) use the methods learned in this course as a foundation for more advanced biostatistics courses.
Content: A more detailed course outline is available here. In brief, the course will cover:

Topic:

Moore & McCabe

Data collection, description, and display

Chapters 1, 3
Probability, Discrete and continuous distributions
Randomness and random variables
Bayes’ Theorem
Diagnostic tests

Chapter 4, 5.1
Inference for means
Sampling distributions
Inference and estimating with confidence
Hypothesis testing
Paired and unpaired data
Sample size and power

Chapters 5.2, 6, 7
Inference for proportions
Paired and unpaired data
c2 test
Fisher’s exact test
Inference for epidemiologic parameters (RR, OR)
Sample size and power

Chapter 8
Nonparametric statistics
Sign test
Wilcoxon rank sum
Wilcoxon signed rank test

Chapter 7, 15
Regression and correlation
Pearson correlation, Spearman correlation
Kendall’s tau
Least squares regression
Coefficient interpretation

Chapters 2, 10                                                                                  
Texts: Required text:
Moore D and McCabe G. Introduction to the Practice of Statistics, Fifth Edition. 2006. Freeman and Company.

Recommended resources:
Armitage P, Berry G, and Matthews JNS. Statistical Methods in Medical Research, Fourth Edition. 2002. Blackwell Scientific Publications.

Colton T. Statistics in Medicine. 1974. Little Brown.
Equipment: Hand calculators (with square root, log, and exponential function) are required.  The R software package will be introduced and used for in-class illustrations. R is available under GPL (free) at http://lib.stat.cmu.edu/R/CRAN.
Evaluation: 5-6 assignments                                                                                      15%
Mid-term exam                                                                                       30%
Project                                                                                                        15%
Final exam                                                                                                40%


The final grade will consist of a letter grade. This will be determined by taking the maximum of:

                   (Homework/Project 30% + Midterm Exam 30% + Final exam 40%)

and                                  (Homework/Project 30% + Final Exam 70%).

 
The midterm will be held in class Monday, October 22 in Purvis Hall, Room 25 (closed-book).
The project is due Monday, November 26 at 11:05.
The final will be held Friday, December 7 2-5pm, location TBA (closed-book).


No make-up work will be allowed for assignments unless a valid & demonstrable reason is presented
within 1 week of the original due date.
Comments: October 8, 2007, is a holiday (Thanksgiving). Note that Tuesday, October 9 follows a Monday schedule and class will be held at the usual time and place.

Note on academic integrity:
McGill University values academic integrity.  Therefore all students must understand the meaning and consequences of cheating, plagiarism and other academic offences under the Code of Student Conduct and Disciplinary Procedures (see http://www.mcgill.ca/integrity/ for more information).



NOTES AND HANDOUTS



ASSIGNMENTS & SOLUTIONS
(and sample final projects)