Ready to make a real difference? Are you interested in applying cutting-edge statistical and machine learning techniques to develop and apply innovative network models uncovering psychopathology in adolescence? Join our interdisciplinary team! We're seeking a highly motivated and interested PhD candidate who aspires to make meaningful impact in the field. Apply now for this exciting PhD project and be part of the future.
Your job The
department of Methodology and Statistics has a job opening for a PhD candidate interested in applying advanced statistical and machine learning techniques to develop and apply advanced network models applicable in Youth Mental Health Research, aiming to improve youth mental health. This interdisciplinary project is a close collaboration between the department of Methodology and Statistics and the
department of Interdisciplinary Social Science.
Adolescence is a phase characterised by heightened susceptibility to mental health problems. Globally, adolescents experience mental health problems, mostly depression or anxiety. Most mental disorders develop during adolescence and have negative long-term consequences. Despite their high prevalence, the progress in understanding and treating mental disorders has been limited. Many mental disorders lack effective treatment options, and sustained recovery is achieved by only a portion of the patients. Furthermore, Comorbidity is widespread among adolescents. The number of adolescents with comorbidity is higher than those with single disorders. However, despite extensive research, identifying underlying causes for mental disorders has been largely unsuccessful.
In this project, you will develop and utilise advanced network approaches to investigate youth mental health. The network approach can be understood as a theoretical framework to explain the existence and development of mental disorders. The essence of the network approach is that the system of interacting symptoms constitutes the disorder, meaning that the causes of the disorder lie in the symptoms and their interactions. The network framework is able to provide a new perspective on why mental disorders co-occur, implying that comorbidity is an inherent feature of mental disorders.
The aim of this project is to uncover dynamic symptom development investigate the interdependence between disorders, symptoms and comorbidity, and inform new targeted interventions based on insights from these developments. You will implement the developed innovative algorithm in this project in a statistical package within the open statistical software environment. To validate the developed model, you will first conduct an extensive simulation study on the estimation and prediction performance of the developed algorithm then you apply the model on the real data. Specifically, you will use a longitudinal cohort study among adolescents with broadly oriented data with information on social, psychological and physical factors. The data set include variables measuring depression, anxiety, internalising and externalising problems, eating disorders, antisocial behaviour, psychotic symptoms, and several psychiatric diagnoses.
You will work in close collaboration with the supervisory team, and you will be supported and supervised by academic staff from both departments. The responsibilities will encompass:
- developing and applying advanced Network Models using advance statistical and machine learning techniques;
- developing open-access software tools (such as R and Python packages) for applying the newly developed algorithms/models and techniques to real-world datasets;
- writing up findings for publication;
- presenting research findings at leading conferences;
- attending classes and seminars (including those offered at other universities) to further develop thinking and research skills;
- conducting teaching (between 10% and 20%), including undergraduate tutorials.