School of Population Health

Advanced Biostatistics & Statistical Computing (PHCM9517)

image - Advanced Biostatistics & Statistical Computing

Description

This course is offered in two modes: either face to face (on-campus) and fully online.

At the end of this course students will be able to apply advanced biostatistical methods to their public health and clinical research and gain the required statistical skills to write a journal article or a scientific report. In particular, students will be able to correctly select the appropriate statistical analytical method to address specific research questions, conduct the analysis using statistical software, present and interpret the results appropriately and draw valid and insightful conclusions. The broad topics that will be covered in this course include: one-way analysis of variance, simple and multiple linear regression analysis, model building strategies in regression analysis to adjust for confounding and dealing with effect modification; logistic regression analysis for binary outcome data, regression analysis for count data (Poisson and Negative binomial regression), and analysis of time to event data. The learning method will include formal lectures on the topics, hands-on problem solving tutorials and computer laboratory sessions to demonstrate the use of statistical software.

Credit points

This course is an elective course in the postgraduate programs within the School of Population Health comprising six units of credit towards the total required for completion of the study program.

A prerequisite for this course is PHCM9498 or PHCM9795.

Mode of study

External (Distance) and Internal (Face-to-Face) classes on campus.

Course aim

This course aims to enable you to apply advanced biostatistical methods to address public health research questions. In particular, it aims to support you to reach a level of proficiency where you will be able to select the appropriate statistical analytical method to address specific research questions with a given data set, conduct the selected statistical analysis using Stata, present and interpret the results appropriately, and draw valid and insightful conclusions about the research question.

Course Outcomes
Upon successful completion of the course you will be able to:
  • Determine the appropriate statistical analytical technique for different epidemiological study designs and datasets.
  • Conduct statistical analysis using advanced techniques on complex datasets with different types of variables.
  • Demonstrate an understanding of issues arising from the application of modelling techniques in statistical analysis and appropriate procedures to handle these issues. Key issues include: confounding and effect modification in epidemiological studies, model building strategies and model diagnostics.
  • Correctly interpret results and draw valid conclusions addressing the research question.
  • Critically discuss results and present findings at a standard that is sufficient for submission to scientific journals or reports.
Learning and teaching rationale

The course focuses on developing practical experience that will assist your understanding and application of statistical techniques and in using Stata software. The focus is to provide you with the capacity to think critically about epidemiological questions and the use of advanced biostatistical methods to address questions in medical and public health research.

Teaching strategies

The course comprises of lectures and tutorials. In addition to the lecture materials, extra learning materials may also be posted on Moodle. The course covers five different analytical techniques used in public health and medical research. These include analysis of variance (ANOVA), simple and multiple linear regression for continuous outcome variables, logistic and log binomial regression for binary outcome variables, Poisson and negative binomial regression for counting variables, and survival analysis for time-to-event data. 

All students should attend (online) or view the 2.5-hour online lecture each week. In addition, there is a weekly 1-hour tutorial. Lectures are structured to introduce basic concepts, application of techniques, and interpretation of results in the first hour. A demonstration of the Stata program in applying the methods discussed with a real dataset is the focus of the last hour of the lecture session. 

Assessment

1. Take home test
Weighting: 15%

2. Assignment 1 - Research Project
Weighting: 45%

3. Assignment 2
Weighting: 40%

Learning resources

Learning resources for this course consist of the following:

  • Course notes and recommended readings from journal articles and text books.  Specific reading lists are provided at the end of each module.
  • Links to all the journal articles and available e-books from the recommended texts will be embedded on Moodle.
  • Links to the scanned copies of relevant chapters from other books will also be available on Moodle.  
  • Stata software for students - Stata 16 will be available in the Wallace Wurth computer lab G6/G7 which will be accessible to enrolled students. Additionally, Stata 16 will be available through UNSW myAccess.