Hacker News Reader

It will be interesting when they realize that it's not a "crisis", but that it is what it is and that psychological phenomenon are just too variable (in time and space) to be reproduced.

View on HN

The whole point of statistics is dealing with those variable phenomena in psychology. Variability is the starting assumption. IMO, we need to find new methods of discovering non-variable and reproducibe phenomena. I like the theory that goals are relatively constant while means (behavior) are variable. The problem is to discover the goals.

I think that the goals you describe are already discovered, they're just used in a different field of "study": marketing.

Statistics has plenty of tools for describing variable phenomena.

Yes, for periodic or well-behaved phenomena. But for most cases you can't summarize human behaviour into one or two variables.

But for most cases you can't summarize human behaviour into one or two variables.

And statistics is a useful tool separate those cases from the few cases where you actually can.

This seems like a strawman--I don't think any part of behavioural science/psychology is claiming to be able to do this.

Reply on news.ycombinator.com