The Medical Statistics Team run a series of annual courses which are open to University staff, NHS staff and external non-statisticians.

  • Introduction to SPSS
  • Introductory Medical Statistics
  • Intermediate Medical Statistics: (all three days as a package or individual days)
    • Day 1: Modelling continuous outcomes - linear regression
    • Day 2: Modelling binary outcomes - logistic regression
    • Day 3: Modelling time to event outcomes - survival analysis

The courses would be useful to anyone working in the field of medicine wishing to broaden their knowledge in research methodology or medical statistics. Further information on course content can be found below and please visit the feedback page to see some comments from previous students. 

Please note that these three courses run just once a year, usually in March/April. Attending all three courses is allowed, but this is not recommended for people who have no previous experience as they are likely to find the pace of the Intermediate Medical Statistics course too fast.

Queries about these courses can be directed to Morag Mcconnell (m.m.mcconnell@abdn.ac.uk), Tel 01224 437266.

Introduction to SPSS

The course is aimed at clinical and non-clinical researchers and other health care professionals who would like a basic introduction to using the SPSS statistical software package.

This course offers a practical guide to using SPSS for Windows. Topics covered by this course include:

  • data entry
  • exploring and summarising data
  • manipulating data
  • data transformations
  • data checking

Format of the course: There will be short demonstrations followed by opportunities to work your way through the course handbook at your own pace. Please note that this is not a course on statistics.

Introductory Medical Statistics

The course is aimed at individuals who are required to interpret and/or conduct basic statistical analyses. The course would be relevant to clinical and non-clinical researchers and other health care professionals. 

The course will cover the following topics:

  • Issues of study design
  • Types of data
  • Descriptive statistics
  • Probability and distributions
  • P-values and hypothesis testing
  • Confidence intervals
  • Univariate techniques (t-tests, correlation, chi-square tests)

Format of the course: A series of lectures aimed at practical application rather than theoretical formulae. No previous knowledge is assumed.

Intermediate Medical Statistics

All three days as a package or individual days

The format of these courses: a mix of lectures and computer practicals using SPSS. This will enable participants to gain experience of the theory and practical application of the statistical techniques, as well as interpretation of the accompanying SPSS output.

A basic knowledge of statistics including p-values, hypothesis testing and simple statistical concepts is assumed for all of the following courses. Prior experience of a statistics package or spreadsheet is desirable, but not essential.

The courses would be relevant to clinical and non-clinical researchers and other health care professionals.


Day 1: Modelling continuous outcomes - linear regression

The aim of this course is to introduce participants to more advanced statistical techniques for measured (continuous/discrete) health outcomes. This will enable participants to gain experience of the theory and practical application of the statistical techniques, as well as interpretation of the accompanying SPSS output.

The course will cover the following topics:

  • Analysis of variance
  • Linear regression

Day 2: Modelling binary outcomes - logistic regression

The aim of this course is to introduce participants to more advanced statistical techniques for binary and categorical health outcomes. This will enable participants to gain experience of the theory and practical application of the statistical techniques, as well as interpretation of the accompanying SPSS output.

The course will cover the following topics:

  • Relative risks, odds ratios, and numbers needed to treat
  • Logistic regression

Day 3: Modelling time to event outcomes - survival analysis

Survival analysis (or time-to-event analysis) allows the examination of a relationship between patient information recorded at some origin (e.g. referral to secondary care, disease diagnosis) and a binary outcome that may or may not occur at some later point (e.g. death, recovery, hospital discharge). Some underlying theory will be explained, but only enough to facilitate interpretation of the analysis.

Those with no knowledge of multivariable statistical modelling are strongly encouraged to attend the previous two Intermediate Medical Statistics courses (3 and 4) before attending this course.

The course will cover the following topics:

  • Censoring and the hazard function
  • Estimating the survivor function using the Kaplan-Meier method
  • Comparing groups using the log-rank test
  • The Cox proportional hazards model
  • Model checking procedures