Serving Forecasting Models
Beyond simply describing reality, statistics can also help, by modeling a situation using appropriate probabilistic formulas, to predict its plausible evolutions in the future. 'Mixture models' are a complex example that makes it possible to identify different classes within a population and... predict that of a new individual to, for example, offer them content or products that might interest them on provider platforms. In the field of health, forecasting models make it possible to improve patient care to the point of imagining personalized medicine. In sports, the analyses lead to dosing the quantity of training as well as possible that optimizes individual performance, and, in the collective context, progress goes as far as predicting the winner of the next FIFA World Cup from past performances!
All articles in this folder
Statistical mixture models explained | Tangente
How can we estimate a model's parameters from a sample whose members come from several different subpopulations that have been mixed together, when information about which one each belongs to has been lost? Several methods are available, depending on the requirements and assumptions, including the famous EM algorithm.
Alain Desrosières: numbers are not neutral | Tangente
A graduate of the École polytechnique (class of 1960) who was deeply engaged with political and civic issues, Alain Desrosières (1940–2013) chose the École nationale de la statistique et de l’administration économique and became an Insee administrator in 1965.
Catherine Com-Nougué and biostatistics | Tangente
Many biostatisticians in academia and the private sector were trained by Catherine Com-Nougué (1944–2017) and impressed by her gifts as a teacher.
Modeling sports training with mathematics | Tangente
Modeling the relationship between performance and training is a delicate statistical problem. Seeking a mathematical model that links these two sets of data means thinking about sport and the potential effects of an athlete's efforts on their results.
Modelling a football match using the Poisson distribution | Tangente
How can you estimate your favourite team's chances of winning the next FIFA World Cup? To some extent, mathematics and artificial intelligence make this possible. Here is an example from the 2018 tournament.
Future medicine: AI and medical statistics | Tangente
How can we predict the outcome of a treatment before testing it on a patient? How can we choose the best treatment for that patient? All of this relies on statistics and, in particular, on artificial intelligence to improve medicine tomorrow—and already today.