Showing posts with label silly statistics. Show all posts
Showing posts with label silly statistics. Show all posts

Wednesday, 11 November 2015

Estranged Notions: Are Religious Kids Really Less Altruistic?

Today's post:

Are Religious Kids Really Less Altruistic?

Briggs snarks at the recent study that's been doing the rounds (which I hadn't bothered to look at in any detail though I'd seen mentions of it). However, of the criticisms I've now seen this is possibly the worst; Briggs waxes sarcastic about the fact that it's the parents' religiosity which is measured, which completely misses the point, while not actually bringing any serious criticism to the table. The biggest weakness of the study is probably that it's interpreting dictator-game outcomes as a measure of ‘altruism’, which seems extremely open to question.

The fact that this is a Templeton-funded study is enough for me personally not to take it very seriously, but I do notice that some religious critics of the study (looking at you Yancey) are quick to point out that the lead researcher identifies as a ‘secular Jew’ while not mentioning that the funding source has a strong pro-religion bias.

As for the statistics, if we put aside the question of whether the dictator-game outcome means anything, the results do at least suggest that religion does not have a large positive effect on this outcome (regardless of whether the negative effect is real or not). But the fact that the breakdown by country is not given—only the researcher's conclusions about various correlations or lack thereof—makes it hard to know whether or not Simpson's paradox or other ecological fallacies are in play or have been properly accounted for. So on balance I don't think the study updates any of my own beliefs to any real extent.

Monday, 27 October 2014

Estranged Notions: Do Atheists Believe in God After All?

Today's post:

Do Atheists Believe in God After All?

A pretty silly study on the whole; the issues of small sample size and high variance have already been pointed out by PBR. Even Horn spots the methodological issue of not using a known-nonexistent deity or similar as a control (to which I'd add, they should also have considered using one from a culture foreign to the study participants).

A possibly more serious issue is the issue of conflation of "believe" and "have an emotional reaction to", the problem with which should be obvious.

Horn also demonstrates his ignorance of the nature of delusions (quoting the idiotic "poached egg" comparison). This is best answered with this piece from Scott Alexander.

Wednesday, 28 May 2014

Estranged Notions: Do ‘Religiously Knowledgeable’ Atheists Believe in God?

Today's post:

Do ‘Religiously Knowledgeable’ Atheists Believe in God?

Short version: survey statistics are not worth much, especially in fringe small-N subcategories of larger surveys. (A proportion — sometimes a nontrivial one — of any survey sample are people giving a purely random or maliciously hostile response; for unpopular or socially marginalized beliefs this can easily skew the results. It has also been found that Americans overstate their religious observance and beliefs to pollsters.)