Experimental design in preclinical research: the good, the bad and the ugly - ONLINE
Thursday, 16 July 2020, 10am to 4pm
COURSE FULL This interactive online MSD Skills training course is suitable for postgraduate research students and early career researchers wanting to understand the issues underpinning good experimental design, the bedrock of reproducible science.
This interactive course will run over two sessions 10-12 and 2-4. It is planned that the day will be split into two 1 hour morning sessions divided by a half hour tea/coffee break, a 90 minute lunch break, then two 1 hour afternoon sessions divided by a half hour tea/coffee break. However, depending on the needs of the group, the tutor may slightly change how the morning and afternoon slots are organised.
This course addresses some of the fundamental issues behind designing good experiments (focusing on pre-clinical experiments exclusively), the bedrock of reproducible science. Arguably, all good experiments start with a good experimental design. Experimental design in the Biomedical Sciences is mostly about logic, common sense and the systematic application of relatively simple techniques to produce unbiased experimental results and reduce variation. This is good news because this should be relatively straightforward. Yet this is where the biggest blunders continue to be made, including by experienced biologists, with demonstrably expensive consequences on results. The course will deal with those concepts, their links with statistical analyses generally and some of the traps that we have all fallen into. We will also address statistical issues relevant to animal research depending on the composition of the audience, in a session where the words “enjoyment” and “statistics” can hopefully share the same sentence.
At the end of the course, attendees should be able to:
- Describe some of the factors affecting reproducibility and external validity, the possible causes of bias and ways of alleviating it
- List the different types of formal experimental designs, and explain the concept of variability, its causes and methods of reducing it
- Identify the experimental unit and recognise issues of non-independence (pseudo-replication)
- Describe the six factors affecting significance, including the meaning of statistical power and “p-values”
- Identify formal ways of determining sample size
- Explain the fundamental principles behind the output of an ANOVA, including “blocking” and “interactions”
A series of interactive online lectures and scenarios delivered by Manuel Berdoy (BMS, Oxford), using Teams.
You will need a good internet connection and uninterrupted time for the live interactive sessions via Teams and you will be asked to access the Vevox audience response system made available during the session, as well as the supplementary materials made available to you in Canvas.
There is no automated workflow for this course. We will do our best to send you emails confirming booking as soon as we can. Supplementary materials will be made available via Canvas (for those booked on the course) a week or so before it starts, and you will also be sent a brief survey you will need to complete prior to the course.