XClose

Statistical Science

Home
Menu

Statistical Science Seminars

A seminar series covering a broad range of applied and methodological topics in Statistical Science.

*** All talks will take place online until further notice ***

Usual time: Thursdays 14:00-15:00

Location: Zoom

Please email thomas dot bartlett dot 10 at ucl dot ac dot uk to join the mailing list, and receive the links to the talks.

Recent talks

Please subscribe to our Youtube channel, to view some recent talks from the series:

https://youtube.com/channel/UC6wQjF2n27k6a_TRO4GjPEg

Upcoming talks
 

8 July 2021: Adrienne Leonard (Cirium / Pivigo) - Predicting Disruption in Uncertain Times

Flight disruption costs airlines between $25B and $35B annually in a typical year. Factoring in the estimated cost to travellers, businesses, and the rest of the aviation ecosystem, that cost rises to around $60B. And that doesn't account for major, global disruption events such as the COVID pandemic, which has affected the aviation industry particularly sharply over the last 18 months. There are many ways that industry players work to mitigate the impact of disruptions, but a key question we have been asking ourselves at Cirium is can we predict delays before they happen and give airlines, airports, ground crews, and passengers advance warning of likely delays to allow them to better plan for and mitigate the effects of these delays? 

In this presentation, I will describe our approaches to modelling and forecasting delays. I'll start with the basic pre-COVID objective: using historical flight data to predict where delays are likely to occur, and to forecast the knock-on effects of those delays on the wider flight network. I will then move on to describe the application of language modelling and transfer learning to improve the quality of delay predictions by uncovering hidden relationships between features in our model via embeddings. Finally, I will tackle the question of how to deal with changing ground conditions - such as the COVID pandemic - where historical training data is no longer representative of the current ground truth. Using the framework of Concept Drift, I will describe how changing conditions can be automatic

15 July 2021: Magali Tournus (Penn State) - How to recover the fragmentation rate and kernel characterizing a size-structured population undergoing fragmentation?

We consider a suspension of particles that undergo fragmentation. We address the question of estimating the fragmentation parameters – i.e. the division rate B(x) and the fragmentation kernel k(y,x) – from measurements of the size particles distribution at various times. This is a natural question for any application where the sizes of the particles are measured experimentally whereas the fragmentation rates are unknown. The application that drives our work is the study of mechanical properties of amyloid fibrils that undergo fragmentation (are the mechanical properties related to toxicity?). In this talk, I will present the biological questions that motivate our work and the new experiments performed by Wei-Feng Xue team at Canterbury, then I will explain why the inverse problem is well posed under reasonable assumptions, and I will focus on how we can recover the fragmentation rate and kernel in practice.

22 July 2021: Takoua Jendoubi (UCL) - A framework for integrative analysis of longitudinal metabolomic data

Metabolomics time-course experiments provide the opportunity to understand the changes to an organism by observing the evolution of metabolic profiles in response to internal or external stimuli. Many statistical methods currently used to analyse short time-series omic data are i) prone to overfitting or ii) do not take into account the experimental design or iii) do not make full use of the multivariate information intrinsic to the data or iv) unable to uncover multiple associations between different omic data. The model we propose is an attempt to i) overcome overfitting by using a weakly informative Bayesian model, ii) capture experimental design conditions through a mixed-effects model, iii) model interactions between variables by augmenting the mixed-effects model with a conditional auto-regressive (CAR) component and iv) identify potential associations between heterogeneous omic variables.

Affiliated Seminars