Melanie Campell

Current research project

Everything Changes Over Time: Transforming Joint Modelling Methodology

Joint models enable the relationships between survival and longitudinal data to be mathematically represented, frequently linking a linear mixed effects model to a Cox proportional hazards model. Despite the significant growth in this field of research in recent years, a wider array of models is needed to truly represent natural biological changes over time. This research aims to transform joint modelling methodology to both allow a better representation of changing effects over time and to handle the common situation where not all patients will react the same to treatments as the population. To do so, a stochastic component would be incorporated within a robust linear mixed effects models to represent the longitudinal process. This would accurately model fluctuations in an individual’s own average longitudinal response over time whilst down weighing the negative impact of longitudinal outliers. In doing so, this would provide more precise interpretations and dynamic predictions.

Biography

After leaving school in 2015, I began an undergraduate degree in Mathematics at Queen’s University Belfast. During the degree I developed a specific interest in Statistics and as a result, took the opportunity to transfer to the integrated Masters course specialising in Statistics. In my final year, I experienced independent research when I was assigned a dissertation on the topic of multilevel modelling under the supervision of Dr. Lisa McFetridge. It was during my final year, I became interested in staying at university to continue my study and new found interest in statistical research. I graduated with an MSci Mathematics and Statistics and Operational Research in June 2019 and subsequently embarked on a three and a half year PhD in October 2019.

Research interests

• Joint Modelling

• Survival Analysis

• Longitudinal Models