This flexible course covers the fundamental elements of bioassay statistics. It explores the basics of analysis and assay development, through to assay optimisation, validation and long term management in routine use. The course will provide a solid background knowledge of the statistical methodology used sufficient to understand and resolve issues that can cause problems with real world data analysis.
Our bioassay statistics training course is designed to give an overview of the statistics behind your bioassay. Our expert statisticians lead the way, using their years of experience to highlight useful tips and tricks for your next bioassay.
We don’t assume any prior knowledge of biostatistics, so the course is perfect for any background, whether you’re working in the lab, in QA, or beyond!
We offer our Bioassay Statistics Training in two types:
We hold regular open training courses where you can learn more about bioassay statistics alongside fellow members of the community from around the world. These courses are held online, and are typically split over two days.
Our next open training course will be held on June 3rd-4th 2025!
Follow Quantics on Social Media and Subscribe to our blog to be the first to hear about all our training courses!
In our tailored courses, we deliver a exclusive training to you and your team. Choose the modules most relevant to your work, or enjoy our full offering of 10 insightful modules detailing the nuances of bioassay statistics. These courses can be held in-person or online, and can be scheduled to suit your schedule.
Please get in touch using the form below if you are interested in a tailored training course.
If you are interested in arranging a training course, or if you have any questions, please don’t hesitate to get in touch with our Training Coordinator, Jason Segall, using the form linked here:
Or visit our Contact Us page:
This module starts with an explanation of what relative potency is, and why it has become accepted by both the industry and regulators as the standard way of reporting potency. The basics of how relative potency is calculated are covered, as well as an introduction to the concept of parallelism. We also take a brief tour of the regulatory guidance for bioassay, which underpins the majority of the training.
Next we introduce the concept of continuous and binary data in bioassay, and examine different ways these are modelled. In the former case, we discuss linear, slope ratio, 4PL, and 5PL models, and, for the latter, we examine logit and probit models. We demonstrate how relative potency is calculated for all covered models.
We then discuss some of the nuances of modelling bioassay data, covering model fitting, variance homogeneity, and response transforms in detail.
In this module, we take a deep dive into the concept of parallelism. We examine why it is so vital for calculating relative potency, and look at how testing for parallelism is performed. In particular, we discuss significance testing–with particular focus on the F Test–and equivalence testing, before examing the pros and cons of both methods.
Here, we introduce system and sample suitability criteria. These, respectively, check the assay is performing as expected, and that our samples are behaving as expected. Several examples of suitability criteria are discussed, including goodness-of-fit and precision factor, along with testing methods. Finally, we provide some tips and tricks for using these concepts in real bioassays.
This module examines the controversial topic of outliers. We discuss methods of detecting statistical outliers, such as Grubbs’ Test, as well as modelling methods which can accommodate outliers, such as robust regression. We also highlight some of the pitfalls of outlier removal, before concluding with a summary of Day 1 through selected examples.
Here, we introduce assay leaning, which aims to make assay design more efficient without reducing precision. Several optimisation methods are discussed, including dose and replicate reduction and suitability criterion choice. We also take a brief look at variance components analysis, as well as examining the pros and cons of leaning at different points of the bioassay life cycle.
In this module, we tackle the theory behind bioassay validation, which is used to prove an assay meets its suitability criteria to regulators. We discuss validation of accuracy, precision, and range, as well as introducing the basics of the design of a validation study.
We follow on from the theory of validation with a demonstration of applying these ideas to a real dataset. We perform calculations to find an appropriate number of runs for the validation, before performing that validation for the accuracy and precision for our example data. We take a brief look at the varaince components of our dataset, before concluding with an assessment of the assay range and suitability criteria.
This module describes the process of continued monitoring of bioassays to check their performance through routine use. We discuss how to choose which endpoints to monitor, and what rules should be imposed on incoming data to ensure the assay is continuing to behave as expected. Finally, we provide recommendations for avoiding common traps in setting up assay monitoring.
Our final module covers the statistics behind avoiding re-validation when an assay is transferred to a new site, including setting acceptance criteria on comparability and variability. We then examine reference bridging, with the reasons behind changing references discussed, along with ways to measure the behaviour of a bioassay with a new reference standard.
Find out more about our Bioassay services: https://www.quantics.co.uk/biostatistics-services/bioassay-development-2/
