For Yet Better Science

The “New Statistics” emphasizes effect sizes, confidence intervals, meta-analysis, and the use of Open Science practices. We present three specific ways in which a New Statistics approach can help improve scientific practice: by reducing overconfidence in small samples, by reducing confirmation bias, and by fostering more cautious judgments of consistency. We illustrate these points through consideration of the literature on oxytocin and human trust, a research area that typifies some of the endemic problems that arise with poor statistical practice.  

This meeting gave behavioural scientists the chance to learn about the latest research technologies for collecting 'big' high-quality data. Data scientists and technology experts explained the latest developments, challenges and benefits of research technology in a series of cutting-edge talks. Attendees also had the opportunity to gain hands-on experience with various research technology tools during interactive showcase sessions.  

ORWH hosted the  5 th  Annual Vivian W. Pinn Symposium , which was presented by NIH and the Foundation for the NIH. This year’s meeting, titled “Integrating Sex and Gender into Biomedical Research as a Path for Better Science and Innovation,” illustrated the scientific, societal, and economic opportunities for integrating sex and gender considerations into biomedical research.  

Negative comments, regardless of their merit, could sway readers’ perceptions  

I’ve been aware of Leonid Schneider’s expose blog ever since the piece on the supposed  fraud of Nobel prize-winner Gregg Semenza  appeared on my Twitter feed. Schneider portrays himself as an  under-dog ; the self-styled “ failed scientist ” has taken a liking to pillaring the hypocrisies of the scientific establishment. To be honest, although criticisms of the undertakings of science are always needed, especially when it concerns matters of data integrity, publishing practices, and perverse incentives in academia, I am a bit weary of uncritically listening to someone who appears to have no established career in either science or science journalism (the only pieces published under his own name appear only on the blog he runs). And his pieces do come off with a bit of crankiness – reading them alone one would think that the scientific establishment is infested with data forgery, devised by scientists whose only wish is to publish in fancy journals at any cost.

The best science for better  lives. Explore the latest high-quality research from The Lancet Group.  

Goal:  I'm aiming for Better Science, especially in psychology and related areas. I have proposed a reconceptualization of significance testing, a tutorial for data testing, and a clarification of p-values, significance, and meta-analysis; I'm also discouraging the use of NHST and substituting Fisher's and Neyman-Pearson's approaches instead. I have also developed a procedure for Sensitiveness Analysis (similar to Power Analysis but more appropriate when we know nothing about the alternative hypothesis). I will seek to expand into confidence intervals and hypothesis testing (Bayesian statistics) in the future