Re:Rally, a novel privacy-first data sharing platform
by thayne on Friday June 25, 2021 @07:51PM
(#27637646)
But if the participants are limited to people who are motivated solely by participating in research, wouldn't that add significant bias to that research?
[ Parent
| on HN ]
Re:Rally, a novel privacy-first data sharing platform
by 9wzYQbTYsAIc on Friday June 25, 2021 @08:06PM
(#27637762)
Indeed, sampling bias is a large concern.
Nonetheless, much of psychology research conducted in the US has made do with ridiculous sampling bias - the US college student is anecdotally considered to be the most-studied population in the world.
Re:Rally, a novel privacy-first data sharing platform
by yissp on Friday June 25, 2021 @09:46PM
(#27638306)
Doesn't the field of psychology have pretty serious issues with the replicability of their experimental results?
Re:Rally, a novel privacy-first data sharing platform
by 9wzYQbTYsAIc on Saturday June 26, 2021 @12:45PM
(#27643437)
Indeed, anecdotally, if not empirically, that is the case. Nonetheless, psychology is a highly operationalized field.
In other words, every thorough study begins with an assessment and revision of the consensus language being used to describe reality.
On that front alone, psychology is one of the most hard sciences around.
Deep learning is directly attributable to psychology research, for what it is worth.