Explore UCD

UCD Home >

PHPS40460

Academic Year 2024/2025

Biostatistics II (PHPS40460)

Subject:
Public Health & Population Sci
College:
Health & Agricultural Sciences
School:
Public Hlth, Phys & Sports Sci
Level:
4 (Masters)
Credits:
5
Module Coordinator:
Dr Ricardo Piper Segurado
Trimester:
Spring
Mode of Delivery:
Blended
Internship Module:
No
How will I be graded?
Letter grades

Curricular information is subject to change.

This module will build on an introductory biostatistics module, concentrating on more advanced techniques employed in the analysis of epidemiological and medical research. The control of confounding using stratification and regression modelling is described in detail and the distinction between effect modifiers and confounders in an analysis is explained. Linear and logistic regression techniques, including the use of dummy variables and modelling interaction effects, is described. Students will be introduced to the analysis of paired or clustered and repeated-measures data, including two-way ANOVA, repeated-measures ANOVA and the concept of a random effect. Particular attention is paid to the analysis of survival (or mortality) in a cohort study, covering such techniques as multiple logistic regression, the Kaplan-Meier lifetable and Cox regression.

Emphasis throughout is placed on the understanding of computer output and on the interpretation of results. The module is built around the computer packages R and SPSS (student may choose according to preference and previous learning), gives the student a comprehensive and hands-on knowledge of how to perform multiple, logistic or Cox regression, as appropriate, and other advanced techniques using one or both packages.

Prior to attending this module students should have previous training in the use of the R statistical software environment, OR of the IBM SPSS Statistics package, covering data importing and entry, setting data types, running simple descriptive statistics and statistical tests up to one-way ANOVA. Ideally students will bring their own laptops to lectures.

About this Module

Learning Outcomes:

At the end of this module students will be able to:
• Appreciate the usefulness and limitations of statistical modelling approaches to data analysis;
• Be able to choose an appropriate model in a given analysis situation, including assessing appropriateness and choice of covariates and interaction effects
• Use and interpret statistical software for linear, logistic or Cox regression modelling of their data;
• Present the results of regression models using correct and interpretable tables and graphs
• Critically evaluate the 'statistical methods' section of a scientific publication.

Indicative Module Content:

- Linear regression
- Correlation
- Logs and exponentials (revision)
- Logistic regression
- Confounding
- Interaction / effect modification
- Time-to event analyses - life tables and Kaplan-Meier curves
- Cox Proportional Hazards Regression
- Paired and longitudinal analyses with ANOVA

Student Effort Hours:
Student Effort Type Hours
Lectures

20
Tutorial

4
Specified Learning Activities

20
Autonomous Student Learning

80
Total

124

Approaches to Teaching and Learning:
The two-hour classes are a mix of lecture giving the rationale, theory and practical guide to each statistical method or approach, interspersed with active learning micro-sessions, where the students perform guided tasks on their own laptops using a statistical software package - either IBM SPSS or the R statistical software environment (RStudio). After each exercise, the students are taken through the output to assist them in interpreting it, and developing skills in the reporting and critical analysis of statistical results. Some sessions consist predominantly of exercises of this sort, revising the skills acquired throughout the semester.

Requirements, Exclusions and Recommendations
Learning Requirements:

Students should have completed the modules PHPS40010: Fundamentals of Epidemiology, and either PHPS40190: Biostatistics 1 or PHPS41150: Introduction to Biostatistics, or equivalent.

Prior to attending this module students should have previous training in the use of the R statistical software environment, OR of the IBM SPSS Statistics package, covering data importing and entry, setting data types, running simple descriptive statistics and statistical tests up to one-way ANOVA. Ideally students will bring their own laptops to lectures.

For more information, please, contact the module coordinator.


Module Requisites and Incompatibles
Not applicable to this module.
 

Assessment Strategy  
Description Timing Component Scale Must Pass Component % of Final Grade In Module Component Repeat Offered
Assignment(Including Essay): Assignment involving simple data analysis and reporting of results in tabular and graphical form. Week 7, Week 8, Week 9 Standard conversion grade scale 40% No

20

 No
Exam (In-person): Written exam on theory and interpretation of statistical models End of trimester
Duration:
2 hr(s)
 Standard conversion grade scale 40% No

80

 No

Carry forward of passed components
No
 

Resit In Terminal Exam
Summer Yes - 2 Hour
Please see Student Jargon Buster for more information about remediation types and timing. 

Feedback Strategy/Strategies

• Feedback individually to students, post-assessment
• Group/class feedback, post-assessment

How will my Feedback be Delivered?

The assignment is given individualised feedback. There is also general in-class feedback on performance and common areas of weakness and strength.

Name Role
Mr John Loughrey Lecturer / Co-Lecturer
Dr Ricardo Piper Segurado Lecturer / Co-Lecturer
Print this page
Fill in the following details:
Enter the body of your query here.

From time to time UCD would like to send you further information that we feel, based on your enquiry, would be of interest to you.