Analysis of Pretest-Posttest Data: It’s not as straightforward as you might think! - Stats Central Seminar 14 February 2019

Facilities

Experimental designs comparing group differences in change over two time points are common in many areas of research. A pre-post design is a simple way to test the effect of an intervention on mean outcomes, but the statistical analysis does pose some questions for the researcher. This talk will outline some of the analysis options available to analyse two-group, pre-post data, including repeated measures analysis of variance, analysis of covariance, change scores and mixed models.

The talk will be about 30 minutes long and will be followed by (free!) afternoon tea and time for discussion.

Speaker: Nancy Briggs, Senior Statistical Consultant and Manager, Stats Central. Nancy's research interests include: the application of latent variable models, multilevel models and related models to problems in public health, medical research and behavioural sciences; Bayesian statistics; clinical trials.

Date and Time:  Thursday, 14th February 2019, 3.00 to 4.00 pm

Location:  Ainsworth Building (J17), Room G03 | UNSW Kensington Campus