Why So Much Science Doesn't Hold Up and What Quantitative Minds Can Do About It

Home / Events / Industry Talks / Why So Much Science Doesn’t Hold Up and What Quantitative Minds Can Do About It

Why So Much Science Doesn’t Hold Up and What Quantitative Minds Can Do About It

Join Dr. Stephen Weston to explore the challenges of research reliability and reproducibility. This talk examines the limitations of p-values and traditional statistical methods, introduces alternative approaches like Bayesian inference, and highlights open science practices and computational tools that support robust, credible research.

Dr. Stephen Weston
- My Current Time Zone - Europe/London
- United Kingdom, London
- America/Detroit
- American Samoa, Pago Pago
- Argentina, Buenos Aires
- Australia, Melbourne/Sydney
- Bangladesh, Dhaka
- Brazil, Rio de Janeiro
- Canada, Vancouver
- Canada, St. John's
- Chile, Santiago
- Chile, Easter Island
- China, Beijing
- Egypt, Cairo
- Fiji, Suva
- France, Paris
- French Polynesia, Marquesas Islands
- Greece, Athens
- India, New Delhi
- Indonesia, Jakarta
- Iran, Tehran
- Japan, Tokyo
- Kenya, Nairobi
- Mexico, Mexico City
- Nepal, Kathmandu
- New Caledonia, Nouméa
- New Zealand, Auckland/Wellington
- Peru, Lima
- Portugal, Azores
- Russia, Vladivostok
- Saudi Arabia, Riyadh
- Singapore, Singapore
- South Korea, Seoul
- Sri Lanka, Colombo
- Thailand, Bangkok
- Tonga, Tongatapu
- Turkey, Istanbul
- UAE, Dubai
- United States, Denver
- United States, Honolulu
- United States, New York
Tue 9 Dec 2025
18:00 - 19:00 GMT
Online

Book event / Sign up

Event Description

“It’s a difference of opinion that makes a horse race.” Generally attributed to Mark Twain, this quote encapsulates the debate over the usefulness of research amid growing concerns in the scientific community about the replicability, reproducibility and reliability of research findings.

By attending this session, participants will:

Understand the limitations of traditional statistical methods – including p-values and NHST—and explore alternative approaches such as Bayesian inference and effect size estimation.
Evaluate methodological reforms like open science practices and preregistration, and their impact on improving research transparency and credibility.
Gain practical insights into computational reproducibility, including how programming tools can support robust and replicable quantitative research.

Speaker

Dr. Stephen Weston

Dr. Stephen Weston is a visiting professor of computer science at Imperial College where he supervises research by MSc and PhD students. He received his PhD in robust optimal control theory from City University, London. He is also currently a PhD candidate in AI at University College London where he focuses on issues in human-computer interaction at the intersection of generative AI and decision theory. Prior to becoming a PhD student for the second time he spent over 30 years in a variety of front office roles in investment banking, risk management (with JP Morgan and Deutsche Bank) and technology (with Intel).