Date(s) - 14/10/2021
9:00 am - 12:30 pm
- Speaker: Dr Salma Ayis
- Location: online
- Book on Skillsforge, or for clinical staff without a skillsforge login, use our Research Methods form
- Please note, you should have attended Statistics Demystified (Part 1) to attend this course
This is an introductory / intermediate course for anyone who would like to understand more about the statistical tests that are reported in many medical journals; when are they appropriate to use? The course is divided into two parts, and it covers the statistical concepts and methods required for describing and analysing various types of data arising in studies of different designs. Attendance of both sessions is required. The use of specific statistical packages will not be covered.
The course covers important concepts such as confidence intervals and hypothesis testing, as well as issues such as the use of subgroup analysis in trials, and how to deal with confounding in observational studies. Standard statistics (means and odds ratios) will be described as well as appropriate situations for their use. ComMondayly used statistical techniques, such as simple uni-variate tests (t-test, chi-squared test), and multiple variable methods (linear regression and logistic regression) will be introduced using examples.
This course will include the following:
- Summarising and describing data
- The meaning of 95% confidence intervals
- The purpose and principles of hypothesis tests
- Tests involving two variables
- Parametric and non-parametric tests (t-tests, Mann-Whitney test)
- Confounding: what is it and how to deal with it
- Analysing continuous data and the t-test
- Linear regression
- Analysis of covariance
- Analysing categorical data and the chi-squared test
- Logistic regression for binary outcomes
- Choosing the correct statistical test
- Issues with multiplicity (Sub-Groups and Interim Analysis).
By the end of the course, participants should be able to:
- Distinguish different types of data and designs
- Summarise data appropriately
- Understand the concepts of hypothesis testing and confidence intervals
- Choose from a range of statistical methods
- Interpret results and draw conclusions more carefully from sample data.
Who can attend?
The courses are free for health care professionals employed by organisations associated with the National Institute of Health Research Biomedical Research Centre at Guy’s & St Thomas’ and King’s College London:
- King’s College London
- Guy’s and St Thomas’ NHS Foundation Trust
- Royal Brompton and Harefield hospitals
- South London and the Maudsley NHS Foundation Trust
- King’s College Hospital NHS Foundation Trust
Places are booked on a first come, first served basis. If the module is full, your name will be placed on a waiting list and if a place becomes available you will contacted at the latest 72 hours beforehand.
Non Attendance Policy
The courses in this programme are very popular and are often oversubscribed. If you are unable to attend a course you are booked on to you must notify us 72 hours in advance so we can offer the place to someone else.
If you do not attend on the day and are unable to provide a satisfactory explanation you may be removed from future course bookings.
For further information please contact the NIHR Guy’s and St Thomas’ BRC Research Training Programme at BRCTraining@gstt.nhs.uk.