Explainers
How research actually works, in the language you already speak. One piece every few days.
-
What a Retraction Means and How to Check a Paper
A retraction is a journal's formal withdrawal of a published paper because its findings can no longer be trusted, and checking its status takes under a minute.
21 November 2026 -
Open Access Publishing: The Models and Who Pays
Open access publishing makes research free to read, but someone still pays, usually the author's grant or institution, through a fee called an article processing charge.
18 November 2026 -
Why Scientific Papers Are Paywalled, and How to Read Them Free
Researchers write and review papers for free, but publishers charge for access, though preprints and repositories let you read most papers legally at no cost.
15 November 2026 -
Journal Impact Factor: What It Measures and Why It's Hated
A journal's impact factor is the average number of citations its recent papers get, and many scientists say it measures the wrong thing entirely.
12 November 2026 -
What Peer Review Actually Checks and How Long It Takes
Peer review means independent scientists check a study's methods and conclusions before publication, a process that typically takes two to six months.
9 November 2026 -
Relative Risk vs Absolute Risk: Why Headlines Mislead
Relative risk is the percentage change between two groups; absolute risk is the actual change in your chances, and journalists usually report the flashier one.
6 November 2026 -
Reading a Clinical Trial Result: Relative vs Absolute Risk
A drug that cuts relative risk by half might lower your actual risk by only one percentage point, so always look for the absolute numbers.
3 November 2026 -
Confidence Intervals Explained: How to Read Them at a Glance
A confidence interval shows the range of plausible values behind a result, and its width tells you at a glance how precise that finding actually is.
31 October 2026 -
What a Meta-Analysis Actually Does to the Evidence
A meta-analysis combines results from many studies into one estimate, but it only clarifies the truth if those studies were asking the same question well.
28 October 2026 -
Observational Study vs Experiment: Why Diet Advice Flip-Flops
Most nutrition headlines come from observational studies that track habits, not experiments that test them, which is why the advice keeps changing.
25 October 2026 -
What a Randomised Controlled Trial Actually Buys You
A randomised controlled trial sorts people into groups by chance, which cancels out hidden differences and lets researchers credit any gap to the treatment.
22 October 2026 -
How P-Hacking Happens Without Anyone Lying
P-hacking happens when researchers make ordinary, well-intentioned analysis choices that quietly raise the odds of a false positive, with no lie required.
19 October 2026 -
The Replication Crisis Explained: What Broke and What's Fixed
The replication crisis is the discovery that many published findings, especially in psychology, don't hold up when other scientists repeat the experiment.
16 October 2026 -
Why Sample Size Decides If a Study's Headline Holds Up
Sample size matters because small studies throw up bigger, less reliable swings by chance, so a headline from 20 people needs far more scepticism than one from 2,000.
13 October 2026 -
What Is Effect Size? Why Real Effects Can Still Be Tiny
Effect size measures how big a difference actually is, which matters because a statistically real effect can still be too small to notice or care about.
10 October 2026 -
Correlation Isn't Causation: What the Examples Actually Show
Correlation and causation differ because causal claims require ruling out reverse causes and hidden common factors, not just showing two things move together.
7 October 2026 -
How to Tell If a Study Is Reliable in Five Minutes
A reliable study has a clear method, a fair comparison group, a sensible sample size, and no hidden conflicts of interest influencing the result.
4 October 2026 -
Preprints vs Peer Review: What Actually Changes
A preprint is a paper shared online before scientists check it, while a peer-reviewed paper has been scrutinised, challenged and usually revised first.
1 October 2026 -
A P-Value Explained Simply, Plus Three Common Mistakes
A p-value shows how likely your data would be if there were no real effect, not whether the finding is true, important, or unlikely to be chance.
28 September 2026 -
What Statistically Significant Really Means
Statistically significant means a result is unlikely to be due to chance alone, not that it is important, large, useful in practice, or definitely true.
25 September 2026 -
How to Read a Scientific Paper: The Order That Works
Read the abstract, then the figures and results, then the methods, then the discussion, and leave the introduction until last.
21 September 2026
Lucent, once a week
We read the new research and write up what actually holds, in the same plain language as this page. No jargon, no hype, three papers a week.
Read the latest issue