Analysis of Variance Masterclass – 1 June 2022 @ 15:00 (GMT+1/BST)

Analysis of Variance Masterclass

The remote learning package consists of a 2 hour lecture delivered online by one of the Qi Statistics team, together with workshops for you to complete in your own time (solutions and data sets provided), plus a pdf of the lecture notes and email support whilst you are completing the workshop after the course for up to 2 weeks. More than just a lecture and as close to face-to-face training as it can be!

What you will learn from this webinar

We all use Analysis of Variance, but this technique makes assumptions about the underlying distributions in our data – what are these assumptions and do they matter? What is the Central Limit Theorem and why does it matter? In reality what is a large data sample and how far can we go in using ANOVA to analyse data collected on limited scale ranges (including binary data).

We will explain model constraints and the difference between Type I,II and III sums of squares and their link with LSMEANS, using modelling of incomplete consumer tests as an illustration.

Mixed models with random and fixed effects for replicated test data will be covered together with repeated measures analysis which requires assumptions about the underlying structure of the model error term, when should they be used and how are they set up in XLSTAT.

We will also cover the application of nested models to integrate demographics into our assessment of differences between products in consumer tests

Do you understand all the outputs that the software spills out? We will cover standard ANOVA, mixed model ANOVA, repeated measures analysis – when and how it should be used, nested models and models with covariates.

We will also discuss the over reliance on statistical significance in reporting data, the relevance (or not) of multiple comparison tests and alternative approaches that have been recently proposed. All you ever wanted to know about ANOVA!

XLSTAT will be used to analyse data and there will be opportunities for practical work. If you don’t have a licence you can download a 14 day trial version.

XLSTAT can alternatively be purchased (with a discount for the first year) through Qi (available via Qi website when booking, or during/after training course).