research methods
10 posts · all topics
-
Why studying hospital patients can make two unrelated diseases look linked
In 1946 the statistician Joseph Berkson showed that if two conditions each make hospital admission more likely, a sample of inpatients can show a link between them that does not exist outside the hospital. The same trap, now called collider bias, turns up wherever a sample is chosen by the very things being compared.
-
Do people in different cultures disagree about what counts as knowing? The Gettier car case
A 2001 study suggested that East Asian and Western students judge a classic puzzle about knowledge differently, which seemed to threaten a basic method of philosophy. Larger replications found no such difference, and a 23-country study found the same judgement almost everywhere.
-
Do people really find golden rectangles the most beautiful?
Gustav Fechner's 19th-century experiments seemed to show that people prefer rectangles shaped by the golden section. Later studies that changed the method, the instructions or the comparison shapes mostly failed to find a special preference, and the clearest modern finding is that individual tastes differ widely.
-
Why the big nuts end up on top, and why physicists still argue about it
Shake a jar of mixed nuts and the large ones surface. Experiments since the 1980s have offered geometry, convection and even the air between grains as explanations, and the evidence suggests different mechanisms win under different conditions.
-
Does hot water freeze faster than cold?
The Mpemba effect, the claim that hot water can freeze before cold, has been argued over since 1969. Careful water experiments have failed to find it, while physicists have shown that a related effect is real in simpler, controlled systems.
-
Was the hot hand a fallacy after all?
For thirty years the hot hand in basketball was a textbook example of people seeing patterns in randomness. In 2018 two economists showed that the standard test was biased against finding streaks, and that correcting it reversed the classic result.
-
Was there ever a Hawthorne effect at Hawthorne?
The story goes that factory workers produced more whenever the lights were changed, up or down, simply because they were being watched. When economists finally analysed the original lighting data, the famous pattern was not there, though the broader idea that being studied changes behaviour has some support.
-
Do language models gain abilities suddenly as they grow?
A 2022 paper catalogued skills that seemed to switch on abruptly in large language models. A 2023 reply argued many of those jumps were produced by how the tests were scored. Later work suggests both camps captured part of the picture.
-
When AI models have seen the exam: benchmark contamination
AI models are ranked by scores on public test sets, and those test sets can leak into training data. Fresh, matched test sets show real but uneven drops in performance, and not every drop means the model memorised the answers.
-
The third kind of good life
Happiness and meaning have dominated well-being research for decades. A newer proposal argues something important was left out, and the evidence for it is interesting, incomplete, and worth reading carefully.