Biostatistics (Bio-I) Basics in Public Health

Biostatistics (Bio-I):

Basics in Public Health

Course Coordinator:

Dr. Siswanto Agus Wilopo, SU, M.Sc., Sc.D.,

Clinical Epidemiologist, Biostatistician and Demographer of the Department of Reproductive Health, Graduate Public Health Program, Faculty of Medicine, Gadjah Mada University

Address                 : Gedung IKM Lantai 1, Phone: +62-274-565076 or 548156

Email                     : mkia@chnrl.net

Class web-side      : http://www.chnrl.net/mkia-kr

Course Description:

This course provides a practical introduction to statistical methods used in a variety of public health and human service settings. Concepts are illustrated with concrete examples that demonstrate how principles operate and are applied to common public health problems. A computer skill is required to take this course, including word processing. A prerequisite course in mathematics or algebra is recommended but not mandatory.

General Education Objectives:

The primary goal of  area  is to enable the student to use numerical and graphical data in personal and professional judgments and in coping with public health issues.

Learning objectives for area  courses are:

1.     To use biostatistics to solve quantitative problems in public health field, including those presented in verbal form

2.     To demonstrate the ability to use biostatistics to solve real life problems in the public health settings.

3.     To arrive at conclusions based on numerical of biostatistics findings and graphical data

Course Organization:

The lecture will be given twice weekly or depending to our department’s schedule. In general, the class each week will discuss statistical theory while laboratory or tutorial class session is devoted to discussing problem sets relevant to previous lecture (exercise module). See details of the schedule at the website.

Attendance:

Here is part of our  policy on this issue: “Students should attend all meetings of their classes, not only because they are responsible for material discussed therein, but because active participation is frequently essential to insure maximum benefit for all members of the class”. It is important for students to attend every class session. If student do not able to attend all classes, the student should attend the class and laboratory exercise at least 80% of total schedules. Otherwise the student is not allowed to take a final exam. If you miss a class, you are responsible for catching-up on materials covered in the missed class as soon as reasonably possible. You might take a class in other division with the same topic since this course is also taught in other divisions. This will require extra work and effort.

Learning Objectives Specific to the Course:

1.     Understanding the concept of biostatistics, producing data, and type of study

2.     Organize and present data using tables, graphs, and summary statistics

3.     Use probability as a tool for addressing random variation in statistical relationships and explaining  data distribution

4.     Calculate, display, and interpret “rates” and proportions used in studies of health and disease

5.     Calculate and interpret confidence intervals for means and differences in means

6.     Understand the conceptual basis of significance testing  using parametric and non-parametric;

7.     Calculate and interpret statistical tests for means and mean differences (paired and independent samples) using parametric and non-parametric;

8.     Understand the conceptual basis of significance testing, calculate and interpret statistical tests for proportion and proportion differences (paired and independent samples) , including stratification analysis of two by two table (Mantel and Haenszel  test and  log-rank test)

9.     Understand the conceptual basis and to be able to calculate for regression and correlation methods, including to interpret statistical tests for the coefficient regression and correlation

10. Understand the conceptual basis and to be able to analyses for multisample inference,  including analysis of multivariable of categorical data

11. Understand the conceptual basis and to be able to analyses for person-time data (survival analysis) using graph (life table) and semi-parametric (Cox Proportional Hazard Model)

12.                                                                                                                                                                                 Determine sample size requirements for selected types of statistical inferences.

Textbook:

1.     Bowers D (2008). Medical Statistics from Scratch: an introduction for health professionals. Chichester, London, UK: John Wiley and Sons, Ltd

2.     Dawson B and Trap RG (2004). Basic and Clinical Biostatistics. 4th Edition.  Singapore: McGraw Hill. (http://www.clinicalbiostatics.com)

3.     Lang TA and Secic M (2006). How to Report Statistics in Medicine. Annotated Guidelines for Authors, Editors, and Reviewers. Second Edition. Philadelphia: American College of Physician.

4.     Moore D S (2007). The Basic Practice of Statistics. Fourth Edition. New York: W. H. Freeman and Company. (http://www.whfreeman.com/bps)

5.     Rosner B (2006). Fundamentals of Biostatistics, 6th ed.  Belmont, CA: Duxbury Press.

Course Module:

There are 10 modules for this class. Each module contains a set exercise, reading materials, and lecture notes. Each student should complete exercises of each module. Some modules use a data set which will be available on the web-class.

Assignments and Activities

Component Description

% of grade

Homework exercises Homework sets are assigned every week. Late papers will not be accepted.

20%

Participation In-class or  Laboratory problem-solving.

10%

Statistical Reports See handout or information posted on the website.

10%

Exams Midterms and final (closed-book, formula card allowed).

60%

Total

100%

Grades cutoffs:

100-97%

A+

89-87%

B+

79-77%

C+

69-67%

D+

Below 60%

F

96-93%

A

86-83%

B

76-73%

C

66-63%

D

92-90%

A-

82-80%

B-

72-70%

C-

62-60%

D-

Example of a grade calculation:

COMPONENT

% EARNED

X

weight

=

Contribution

Homework  exercises

95

X

.20

=

19.00

Participation

95

X

.10

=

9.50

Statistical report

85

X

.10

=

8.50

Midterm #1

92

X

.20

=

18.40

Midterm #2

82

X

.20

=

16.40

Final

85

X

.20

=

17.00

Weighted average

=

88.80

Grade: B+

Lecturers:

1. dr. Siswanto Agus Wilopo, SU, M.Sc., ScD.

2. Prof. dr. Hari Koesnanto, DrPH

3. drg. Dibyo Pramono, SU, MDSc

4. Drs. Danardono, MPH, PhD

5. Drs. Zulaela, Dipl.Med.Stat, M.Si

Teaching Assistants:

1. Althaf  Setyawan, S.Si

2.     Drs. Abdul Wahab, MPH

3.     drg. T. Baning Rahayujati, M.Kes

4.     dr. Trisno Agung Wibowo, M.Kes

5.     Ki Hariyadi, S.Si

Table Biostatistics Module and Corresponding Lecture

Module

Corresponding Lecture

Lecturer

No.

Title

Due Date

No.

Topics

No. of Session

I Introduction, Describing and Summarizing Data 06/10/08 01. Introduction to Public Health Research:

Why studying biostatistics and epidemiology is important; how this lecture is designed and organized

1

02. Study Designs in Public Health Research:

How to classify study designs; observational studies (cohort, cross-sectional, case-control); experimental studies (clinical trials); meta-analysis

1

03. Summarizing Data & Presenting Data in Tables & Graphs:
Characteristics that are counted (nominal) versus those that are measured (numerical); how to summarize data (mean, median, standard deviation, proportion, correlation, relative and absolute risk ratios, number needed to treat); using tables and graphs to display and summarize observations

2

II. Probability and Statistical Distribution 04. Probability & Related Topics for Making Inferences About Data:
How to use rules of probability; the difference between populations and samples; probability (normal, binomial, Poisson) and sampling distributions (central limit theorem); introduction to statistical inference (confidence intervals and testing hypotheses)

2

Midterm: 1

III Estimation of Statistical Distribution and Concept of Hypothesis Testing 05. Research Questions About One Group:

How to analyze and interpret questions about the mean and proportion in one group (t and z tests); methods when the same group is measured twice (paired t and McNemar tests, kappa); alternatives when the distribution of observations are skewed (nonparametric); how to find the number of subjects needed to answer the research question (power)

2

IV Statistical Tests for two different means and proportions 06. Research Questions About Two Separate or Independent Groups:
How to analyze and interpret questions about the mean and proportion in two groups (t and chi-square tests); alternatives when the distribution of observations are skewed (nonparametric); how to find the number of subjects needed (power)

3

V Comparing Means Among three Groups or More:

Analysis of Variance

07. Research Questions About Means in Three or More Groups:

How to analyze and interpret questions about the mean and proportion in three groups (analysis of variance); multiple comparison methods; methods when the same group is measured twice (repeated measures); alternatives when the distribution of observations are skewed (nonparametric); how to find the number of subjects needed (power)

2

VI Assessing Association Among Continues Variables 08. Research Questions About Relationships Among Variables:

Finding and testing correlation coefficients (Pearson); other correlation methods; using linear regression to predict an outcome; how to find the number of subjects needed (power)

3

Midterm: 2

VII Comparing Survival  Distribution: Life Table and Kaplan Meier 09. Analyzing Research Questions About Survival:

How to develop and interpret life tables and Kaplan-Meier survival curves; comparing two survival curves; the concept of hazard; intention-to-treat principle

1

VIII Analyzing One Dependent Variable with Many Independent Variables 10. Statistical Methods for Multiple Variables:

Using multiple regression to predict an outcome; controlling for confounding variables (analysis of covariance); predicting a nominal outcome (logistic regression); predicting survival (proportional hazard model); meta-analysis.

3

SAW/DP

IX Statistical Methods for Screening and Diagnostic Tests 11. Methods of Evidence-Based Health Care and Decision Analysis:

Evaluating diagnostic procedures; sensitivity, specificity, and predictive values; likelihood ratio; ROC curves; how decision trees (protocols, algorithms) are designed and interpreted; using decision analysis to make decisions for individuals or group and for health policy; comparing diagnostic procedures.

2

X How many subjects do you need for your study? 12 Sample Size Estimation:

Review of statistical methods for continues and discrete data; sample size for a single proportion; sample size estimation for two proportion and two means, sample size estimation regression and correlation; and sample size estimation agreement analysis (kappa)

2

Final Examination

Note: 1 session is about 50 minutes

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: