Essomanda Konzou breaks a scientific bottleneck on Gaussian distributions to improve statistical models

Essomanda Konzou's thesis, defended in 2020 at the University of Lorraine and the University of Lome, made it possible to overcome bottlenecks concerning generalized inverse Gaussian and Kummer distributions. Using Stein's method, this research opens up concrete application prospects in fields such as finance, by improving the accuracy of risk and return models.

Essomanda Konzou's research addresses advanced mathematical concepts, notably generalized inverse Gaussian distributions and Kummer distributions, using Stein's method. This study raises questions about the application of these theories in statistics and probability theory, and aims to establish bounds on the rate of convergence of distributions, which is essential for practical applications.

By establishing bounds for the rate of convergence, the thesis demonstrates how Stein's method makes it possible to solve differential equations associated with Stein operators. This significant advance could transform the way statistical models are designed, particularly in finance, where a better understanding of probability distributions could optimize risk analysis.

The implications of this research are strategic for decision-makers, who could benefit from improved statistical models across various sectors. The application of generalized inverse Gaussian and Kummer distributions could enable more informed decisions, while meeting the growing market demand for more accurate probability models.

« "By solving differential equations associated with Stein operators, I was able to establish bounds on the rate of convergence of distributions, which paves the way for practical applications in fields such as finance." »

« "This research highlights the importance of access to advanced knowledge for improving decision-making models, a critical issue for economic actors in Africa and beyond." »