Hacker News new | past | comments | ask | show | jobs | submit login

Goodness, are you not familiar with the phrase "correlation does not imply causation"?

There are ways to establish causal relationships, the gold standard of which is to conduct a double-blind controlled trial.

To claim as you have that a correlational study establishes a causal relationship is deeply misguided, irrespective of whether or not it is peer-reviewed.




Yes I am - you don't seem to know that all a double-blind controlled trial produces is (at best) a very strong correlation. I'm not claiming that a correlational study implies causation. I'm claiming that ALL statistical analyses can only prove correlation, and never causation. You're wrong about double-blind controlled trials proving causation.


You are factually incorrect.

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7081045/

>In clinical medical research, causality is demonstrated by randomized controlled trials (RCTs).

https://www.sagepub.com/sites/default/files/upm-binaries/236...

https://www.statisticssolutions.com/dissertation-resources/r...

https://www.abs.gov.au/statistics/understanding-statistics/s...

https://www2.stat.duke.edu/~jerry/Papers/causal.pdf

If you argue this further I'm just going to conclude you're trolling and won't respond again.

You are wrong. Face it.


You're confusing strong evidence for causality with establishment and absolute proof of causality. This is even discussed in the sources you've cited (second link). For example here is a quote from one of your sources about the necessity understanding the underlying mechanism before causality can be established:

> A causal mechanism is the process that creates the connection between the variation in an independent variable and the variation in the dependent variable that it is hypothesized to cause (Cook & Campbell, 1979:35; Marini & Singer, 1988). Many social scientists (and scientists in other fields) argue that no causal explanation is adequate until a mechanism is identified.


>If you argue this further I'm just going to conclude you're trolling and won't respond again.

>You are wrong. Face it.


Thank you for demonstrating your willingness to engage with opposing viewpoints even when supporting evidence is presented (;




Join us for AI Startup School this June 16-17 in San Francisco!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: