Communicating Science: The "significance" of Statistics
Statistical significance and scientific importance are distinct, equally valuable aspects of communicating the significance of statistics in research
Send us a link
Here's What the First Two Years of Horizon Europe Look Like in Numbers
Here's What the First Two Years of Horizon Europe Look Like in Numbers
Horizon Europe is heading into its third year, and the latest statistics offer a glimpse of how the EU is spending its €95.5 billion research funding pot.
One Statistical Analysis Must Not Rule Them All
Any single analysis hides an iceberg of uncertainty. Multi-team analysis can reveal it.
Why Do Some People Succeed when Others Fail? Outliers Provide Clues
Adopting behaviors of people who buck trends could boost public health and sustainability. In any large dataset involving the choices people make, a handful of people will succeed when most others like them fail. Zooming in on those outliers and mapping out how they made their choices could give those failing in similar circumstances a leg up.
Are Women Submitting Fewer Grant Proposals?
Studies and surveys confirm that during the COVID-19 pandemic, women's workload at home has increased. Does that mean women researchers are also submitting fewer proposals to the SNSF? Analyses show that, with one exception, their share has remained stable.
Stories, Statistics, and Authenticity in Health Communications
Stories, Statistics, and Authenticity in Health Communications
As the pandemic worsened in the United Kingdom during spring 2020, political disputes turned in a strange direction. The UK government started to claim that the UK’s Covid-19 statistics could not be compared with any other country.
There's No Proof the Oxford Vaccine Causes Blood Clots. So Why Are People Worried?
There's No Proof the Oxford Vaccine Causes Blood Clots. So Why Are People Worried?
It's human nature to spot patterns in data. But we should be careful about finding causal links where none may exist, says statistician David Spiegelhalter
How Scientists Can Stop Fooling Themselves over Statistics
Sampling simulated data can reveal common ways in which our cognitive biases mislead us.
'Every Day is a New Surprise.' Inside the Effort to Produce the World's Most Popular Coronavirus Tracker
'Every Day is a New Surprise.' Inside the Effort to Produce the World's Most Popular Coronavirus Tracker
How a small university team at Johns Hopkins built a COVID-19 data site that draws 1 billion clicks a day.
We're Reading the Coronavirus Numbers Wrong
Up-to-the-minute reports and statistics can unintentionally distort the facts.
The Deceptively Simple Number Sparking Coronavirus Fears
Here's what the oft-cited R0 number tells us about the new outbreak-and what it doesn't.
Statistical Significance Gives Bias a Free Pass
Whether or not "the foundations and the practice of statistics are in turmoil",1 it is wise to question methods whose misuse has been lamented for over a century.
Sorry, Wrong Number: Statistical Benchmark Comes Under Fire
Earlier this fall Dr. Scott Solomon presented the results of a huge heart drug study to an audience of fellow cardiologists in Paris. The presented number 0.059 caused gasps as the audience was looking for something under 0.05.
Ten Common Statistical Mistakes to Watch out for when Writing or Reviewing a Manuscript
Ten Common Statistical Mistakes to Watch out for when Writing or Reviewing a Manuscript
What can authors and reviewers do to keep common statistical mistakes out of the literature?
Textbook Analysis Uncovers Erroneous Explanations of Statistical Significance
Textbook Analysis Uncovers Erroneous Explanations of Statistical Significance
An examination of introductory psychology textbooks suggests that prospective psychological researchers may learn to interpret statistical significance incorrectly in their undergraduate classes.
It's Time to Retire Statistical Significance
While statistical significance sends the so-called significant results into the literature, the results on the other side of the threshold often disappear into the “famous file drawer”.
The Statistics Skirmishes
"Today I speak to you of war. A war that has pitted statistician against statistician for nearly 100 years. A mathematical conflict that has recently come to the attention of the ‘normal’ people."
Statisticians Want to Abandon Science's Standard Measure of 'Significance'
For years, scientists have declared P values of less than 0.05 to be "statistically significant." Now statisticians are saying the cutoff needs to go.
The Guardian View on Statistics in Sciences: Gaming the (un)known | Editorial
Statisticians are calling on their profession to abandon one of its most treasured markers of significance. But what could replace it?
It's Time to Talk About Ditching Statistical Significance
Looking beyond a much used and abused measure would make science harder, but better.
Manipulating the Alpha Level Cannot Cure Significance Testing
Manipulating the Alpha Level Cannot Cure Significance Testing
When evaluating the strength of the evidence, we should consider auxiliary assumptions, the strength of the experimental design, and implications for applications. To boil all this down to a binary decision based on a p-value threshold is not acceptable.
Inferential Statistics, P-Values, and the Quest to Evaluate Our Hypotheses
Inferential Statistics, P-Values, and the Quest to Evaluate Our Hypotheses
P-values and significance testing have come under increasing scrutiny in scientific research. How accurate are these methods for indicating whether a hypothesis is valid?
The Proposal to Lower P Value Thresholds to .005
John Ioannidis discusses the potential effects on clinical research of a 2017 proposal to lower the default P value threshold for statistical significance from .05 to .005 as a means to reduce false-positive findings.
Statcheck - a Spellchecker for Statistics
A study has revealed a high prevalence of inconsistencies in reported statistical test results. Such inconsistencies make results unreliable, as they become “irreproducible”, and ultimately affect the level of trust in scientific reporting.
Inferential Statistics Is Not Inferential
Statistical significance and hypothesis testing are not really helpful when it comes to testing our hypotheses.
Badges for Sharing Data and Code at Biostatistics
Reproducible research includes sharing data and code. The reproducibility policy at the journal Biostatistics rewards articles with badges for data and code sharing. This study investigates the effect of badges at increasing reproducible research, specifically, data and code sharing, at Biostatistics.
Nearly 100 Scientists Spent 2 Months on Google Docs to Redefine the P-Value
Nearly 100 Scientists Spent 2 Months on Google Docs to Redefine the P-Value
A new paper recommends that the label “statistically significant” be dropped altogether; instead, researchers should describe and justify their decisions about study design and interpretation of the data, including the statistical threshold.
×