Event

Missing data is a widespread problem in epidemiological and clinical research. It is particularly pertinent in longitudinal studies where there are multiple opportunities for missed observations and dropout. Multiple imputation is becoming increasingly popular to handling missing data given its flexibility and its availability in statistical packages. However, it may not always be the best analytic approach, particularly if it is not applied appropriately. In this talk I will provide an overview of my research program in missing data and multiple imputation. I will discuss recent developments in analysis planning in the presence of missing data, methods for multiple imputation in longitudinal studies with multi-level data, unequal sampling, and a large number of auxiliary variables, and provide guidance on reporting results from studies with missing data.

Katherine (Kate) Lee is a lead investigator of the ViCBiostat network, a professor of biostatistics at the Murdoch Children’s Research Institute and the Associate Director: Biostatistics of the Melbourne Children’s Trials Centre. She also holds an honorary appointment at the University of Melbourne, is a lead investigator of the Australian Trials Methodology (AusTriM) Research Network, and is co-chair of the  Australian Clinical Trials Alliance Statistics in Trials Interest Group (ACTA-STInG).  She has a BSc in Mathematics, and an MSc and a PhD in biostatistics (University of Cambridge, 2005). 

Her biostatistical research interests are in the method of multiple imputation for dealing with missing data and adaptive platform trials.

Please note new location (same venue):

Seminar Room 515, Level 5

Melbourne School of Population and Global Health

207 Bouverie Street,

Parkville VIC 3053

and online via Zoom

This seminar will be recorded.

Please click the link below to join:

https://monash.zoom.us/j/82804530166?pwd=ZFRGbTlNNmpNd0pvUjJqS1pLU2Yrdz09
Or, go to https://monash.zoom.us/join and enter

meeting ID: 828 0453 0166 and

passcode: 111066