Hacker News Reader

Comment by danamit | Hacker News Reader

Autism seem to be a politicized issue by looking at the replies.

As far as I can tell the paper is nothing but honest truth seeking, you know a study doesn't equal truth, the article itself doesn't say it is a confirmed hypothesis. And while correlation doesn't mean causation, when you see a correlation, the first thing you do is you investigate if it is a causation too. The most logical thing to do and thanks God smart people did that with lead and many other toxic chemicals that affected society in the past.

View on HN

All it tells me is that the standard for evidence in economics is much lower than the standard of evidence in medicine or sociology. This paper has some problems that run very deep in established methodology, so while it might be good faith, it's also useless.

What specific problems are you referring to?

The number of assumptions made without good evidence (neither rain nor having a cable subscription is automatically more TV time - especially the presence of cable says nothing about how parents control their childs media diet and is just an indicator of wealth) and the blindness for alternative explainations for these supposed relationships.

They started from a typical armchair hypothesis and then looked for a way to interpret data to fit that hypothesis. That by itself is not remarkable, but the quality of the interpretation is questionable at best and outright malicious as worst.

They address the connection between rain and TV time in the article:

>The authors first use data from the American Time Use Survey to confirm the link between precipitation and television watching. The results suggest a strong relationship - a child under age 3 watches an average of 27 additional minutes of television on a day with one inch of precipitation (which is equivalent to a day of heavy rain) than on a day with no precipitation.

Sample size: 1.

Conclusion: the standard for evidence in economics is much lower than the standard of evidence in medicine or sociology.

Reply on news.ycombinator.com