Doing Some Good with Machine Learning

It is a pleasure to invite you to our third LSS Presentation of 2021, to take place on June 4, from 8pm – 9:30 pm via Microsoft Teams.

The talk will be given by Prof. Lester Mackey. Lester Mackey is a statistical machine learning researcher at Microsoft Research New England and an adjunct professor at Stanford University. He received his Ph.D. in Computer Science (2012) and my M.A. in Statistics (2011) from UC Berkeley and my B.S.E. in Computer Science (2007) from Princeton University. Before joining Microsoft, he spent three years as an assistant professor of Statistics and, by courtesy, Computer Science at Stanford and one as a Simons Math+X postdoctoral fellow, working with Emmanuel Candes. His Ph.D. advisor was Mike Jordan, and his undergraduate research advisors were Maria Klawe and David Walker. He got his first taste of research at the Research Science Institute and learned to think deeply of simple things at the Ross Program

Abstract

This is the story of my assorted attempts to do some good with machine learning. Through its telling, I’ll highlight several models of organizing social good efforts, describe half a dozen social good problems that would benefit from our community’s attention, and present both resources and challenges for those looking to do some good with ML.

Practical information

Date: 4 June 2021
Time: 20:00-21:30
Place: Microsoft Teams
Fee: Free
Registration: please register by sending an email to Michela Bia (michela.bia@liser.lu)

Vaccine trials in the age of COVID-19: issues and inferences

It is a pleasure to invite you to our second LSS Presentation of 2021, to take place on May 18, from 8pm – 9:30 pm via Microsoft Teams.

The talk will be given by Prof. Stephen Senn. Stephen Senn is currently providing consulting for CCMS since he retired in April 2018 from his position of CCMS head. He joined LIH in 2011 and was previously a Professor in Statistics at the University of Glasgow (2003) and University College London (1995-2003). In addition to working as an academic he has also worked for the pharmaceutical industry in Switzerland and the National Health Service in England. He is the author of three books, Cross-over Trials in Clinical Research (1993 & 2002), Statistical Issues in Drug Development (1997, 2007) and Dicing with Death (2003). His expertise is in statistical methods for drug development and statistical inference. He consults extensively for the pharmaceutical industry.

Abstract

The response to the COVID-19 crisis by various vaccine developers has been extraordinary, both in terms of speed of response and the delivered efficacy of the vaccines. It has also raised some fascinating issues of design, analysis and interpretation. I shall consider some of these issues, taking as my example, five vaccines: Pfizer/BioNTech, AstraZeneca/Oxford, Moderna, Novavax, and J&J Janssen but concentrating mainly on the first two. Among matters covered will be concurrent control, efficient design, issues of measurement raised by two-shot vaccines and implications for roll-out, and the surprising effectiveness of simple analyses. Differences between the five development programmes as they affect statistics will be covered but some essential similarities will also be discussed.

Practical information

Date: 18 May 2021
Time: 20:00-21:30
Place: Microsoft Teams
Fee: Free
Registration: please register by sending an email to Michela Bia (michela.bia@liser.lu)

Dynamical modelling of COVID-19 pandemic and its path towards herd-immunity

It is my pleasure to invite you to our first LSS Presentation of 2021, to take place on March 4, from 8pm – 9pm via Microsoft Teams . The talk will be given by Françoise Kemp from the University of Luxembourg. She got a Master in Applied Mathematics from the University of Trier in 2018, and is now doing a PhD in Systems Biomedicine at the Luxembourg Center for Systems Biomedicine, and is Member of the COVID-19 Taskforce Research Luxembourg

Abstract

Against the current COVID-19 pandemic, non-pharmaceutical interventions have been widely applied; vaccines are also becoming available. Now, an urgent question is how the interplay between vaccination strategies and social measures will shape infections, hospital demand and casualties. Hence, we extend the Susceptible-Exposed-Infectious-Removed (SEIR) model to include vaccination, ICU, hospital and death. We calibrate it to data of Luxembourg, Austria and Sweden. The model quantifies the vaccination rate needed for herd immunity by desired times. Aiming to vaccinate the whole population within 1 year at a constant rate could lead to herd immunity only by mid-summer. Herd immunity might not be reached in 2021 if too slow vaccines roll-out speeds, which we quantify, are employed. Vaccination will help considerably, but not immediately, thus social measures still remain crucial for months.

Practical information

Date: 4 March 2021
Time: 20:00-21:00
Place: Microsoft Teams
Fee: Free
Registration: please register by sending an email to Michela Bia (michela.bia@liser.lu)

Seminar on « The long-run effect of childhood poverty and the mediating role of education »

On Thursday, 10 December 2020, at 13:00, the Luxembourg Statistical Society is proud to welcome  Michela Bia for a seminar on « The long-run effect of childhood poverty and the mediating role of education ».

Ms Michela Bia is secretary of the LSS and she works as researcher at LISER.

The manuscript, co-authored with Luna Bellani, has been published last year on the Journal of the Royal Statistical Society (Statistics in Society) Series A, 2019, vol. 182, n°1, pp. 37-69 .

The seminar will be held online and the link to the presentation wills provided on request.

The study examines the role of education as a causal channel through which growing up poor affects the economic outcomes in adulthood in the European Union. We apply a potential outcomes approach to quantify those effects and we provide a sensitivity analysis on possible unobserved confounders, such as child ability. Our estimates indicate that being poor in childhood significantly decreases the level of income in adulthood and increases the average probability of being poor. Moreover, our results reveal a significant role of education in this intergenerational transmission. These results are particularly relevant for Mediterranean and central and eastern European countries.