On Fri, Jan 10, 2025, 5:33 PM James Bowery <jabow...@gmail.com> wrote:
> > Stop palavering and start doing algorithmic information criterion > macrosocial model selection. > That's what I'm doing when I project past trends into the future. You compress by fitting a line to the data points and encoding the differences. But that only finds correlations, not causations. If we think that A causes B, then we can test P(B|A) > P(B). But you could rewrite that as: P(A,B)/P(A) > P(B) P(A,B) > P(A)P(B) P(A,B)/P(B) > P(A) P(A|B) > P(A) B causes A. For example, in 2014 I wanted to study the relationship between gun ownership and homicide rate, so I compared them by country. I was surprised to find a weak negative correlation (more guns = fewer murders). But it does not answer the controversial question of whether guns prevent crime or crime prevents guns. It does not inform policy. https://docs.google.com/spreadsheets/d/11cblK8k8aXB7Cw0lf8Azr8WLeBvrf6vOureKdkZh5zU <https://docs.google.com/spreadsheets/d/11cblK8k8aXB7Cw0lf8Azr8WLeBvrf6vOureKdkZh5zU/edit?usp=drivesdk> Of the top 30 countries ranked by fertility, all but Afghanistan are in central Africa. The literacy rate for women is below 50% in most of these countries. What would be your suggestion for preventing population collapse? ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tff34429f975bba30-M81a2fb2fb62370476087c01d Delivery options: https://agi.topicbox.com/groups/agi/subscription
