NATIONAL CHIAO TUNG UNIVERSITY

INSTITUTE OF STATISTICS

 

STATISTICAL METHODS FOR EPIDEMIOLOGY

SPRING 2004

 

 

 


Instructor:

Guan-Hua Huang, Ph.D.

 

Office: 423 Assembly Building 1

 

Phone: 03-513-1334

 

Email: ghuang@stat.nctu.edu.tw

Class meetings:

Wednesday 1:30-4:30 pm at 427 Assembly Building 1

Office hours:

By appointment

Class website:

http://www.stat.nctu.edu.tw/faculty/ghuang/course/statepi04/

Credit:

Three (3) credits

 

COURSE SUMMARY

 

This course will cover statistical methods for design, conduct, and analysis of epidemiologic studies such as case-control and cohort studies. Topics include overview of designs for research studies; epidemiologic study design; rates and risk; measures of association; classical contingency table methods; logistic and Poisson regression; and proportional hazard regression. Examples from the literature and data from a number of well-known epidemiologic studies will be used for illustration of the concepts involved.

 

HANDOUTS AND TEXTBOOKS

 

Handouts corresponding to each lecture will be available on the class website before each class. The required textbook for this course is

 

Nicholas P. Jewell (2003). Statistics for Epidemiology. CRC Press.

 

Reading assignments will be made primary in this book. In addition, following books are recommend for further reading

 

Breslow NE, Day NE (1980). Statistical Methods in Cancer Research, Vol. I, The Analysis of Case-Control Studies. International Agency for Research on Cancer, Lyon.

 

Breslow NE, Day NE (1987). Statistical Methods in Cancer Research, Vol. II, The Design and Analysis of Cohort Studies. International Agency for Research on Cancer, Lyon.

 

Hosmer DW, Lemeshow S (1989). Applied Logistic Regression, John Wiley & Sons.

 

PREREQUISITES

 

Students are expected to be familiar with basic epidemiologic concepts. The prerequisite for this course is “Introduction to Epidemiology”, or equivalent.

 

METHOD OF STUDENT EVALUATION

 

The course grade will be based on three homework assignments (30%), one midterm exam (30%), and one final exam (40%).

 

COURSE OUTLINE

 

Readings refer to:

Nicholas P. Jewell (2003): Statistics for Epidemiology (Jewell),

Breslow NE, Day NE (1980): Statistical Methods in Cancer Research, Vol. I (Breslow & Day I), Breslow NE, Day NE (1987): Statistical Methods in Cancer Research, Vol. II (Breslow & Day II), Hosmer DW, Lemeshow S (1989): Applied Logistic Regression (Hosmer & Lemeshow).

 

Module

Topic

Reading

1

Introduction and overview of goals of epidemiologic research and epidemiologic study designs

Jewell

Chapter 1, 5

Breslow & Day I

Chapter 1

Breslow & Day II

Chapter 1

2

Measures of disease occurrence and association:

a.     Different rates

b.     Inferences for rates

c.     Comparing two rates

d.     2×2 table

e.     c2 test and Fisher’s exact test

f.       r×c table

g.     Relative risk and odds ratio

h.     Inferences for relative risk and odds ratio

i.        Introduction to nonparametric methods

Jewell

Chapters 2, 4, 6, 7

Breslow & Day I

Chapter 2, 4

3

Control of extraneous factors:

a.      Confounding and interaction

b.      Mantel-Haenszel method

c.      McNemar’s test

d.      Tests of homogeneity

e.      Test of trend

Jewell

Chapter 8, 9, 10, 11

4

Logistic regression:

a.      Concepts

b.      Model and assumption

c.      Interpretation of regression coefficients

d.      Inferences

e.      Likelihood ratio test

f.        Goodness-of-fit test

Jewell

Chapter 12, 13

Hosmer & Lemeshow

Chapter 1, 2

5

Logistic regression modeling:

a.      Polynomial regression

b.      Hierarchical principal

c.      Collinearity

d.      Dummy variables

e.      Splines

Hosmer & Lemeshow

Chapter 3

6

Confounding and interaction in logistic regression:

a.      Modeling

b.      Assumption

c.      Interpretation

Jewel

Chapter 14

7

Logistic regression for case-control and matched data:

a.      Risk and odds ratio in case-control studies

b.      Logistic regression for case-control data

c.      When there are many strata with few observations in each

d.      Conditional logistic regression for matched data

Jewell

Chapter 16

Hosmer & Lemeshow

Chapter 7

8

Log linear model for grouped data:

a.      Contingency table

b.      Log linear model

c.      Poisson assumption

d.      Goodness of fit

Breslow & Day II

Chapter 4

9

Analysis of survival data:

a.      Examples of survival data

b.      Survival, hazard and cumulative hazard functions

c.      Censoring and truncation

d.      Kaplan-Meier estimator

Breslow & Day II

Chapter 5

10

Proportional hazards model:

a.      Assumption of the model

b.      Testing and estimation

c.      Computing programs and interpreting results

d.      Time dependent covariates

Breslow & Day II

Chapter 5, 6