Isn’t there a way to cut out outliers methodically to get a better picture of the majority? It’s been a long time since I took statistics. I also think these numbers would change if you broke them down to regional or religion or other demographics. A single number for everyone doesn’t tell the whole story.
That also brought up a good point - lots of couples aren’t married (by choice or other reasons) and aren’t in these studies because of that. And then what about same sex couples? The question of age gap still applies to them too in the overall scope of whether people seek out similar ages or not.
In introductory stuff they just say discard outliers by eyeball, but obviously that’s not very rigorous. You can do mathier versions, but it can be considered cooking the data if it changes your conclusion, and can get you in real trouble if you don’t announce it.
I wasn’t even talking about outliers in the data-breaking sense there, though. I really just meant that there must have been a lot of variation because that’s not as big a difference as I was expecting, based on old stories. There’s a few standard ways to measure that, actually an infinite series, but the two you often focus on for “outliers” in this sense are variance (literally just called that) and kurtosis. The higher order ones become increasingly nitpicky.
Isn’t there a way to cut out outliers methodically to get a better picture of the majority? It’s been a long time since I took statistics. I also think these numbers would change if you broke them down to regional or religion or other demographics. A single number for everyone doesn’t tell the whole story.
This post from flowing data gives a different perspective of the same data.
That also brought up a good point - lots of couples aren’t married (by choice or other reasons) and aren’t in these studies because of that. And then what about same sex couples? The question of age gap still applies to them too in the overall scope of whether people seek out similar ages or not.
In introductory stuff they just say discard outliers by eyeball, but obviously that’s not very rigorous. You can do mathier versions, but it can be considered cooking the data if it changes your conclusion, and can get you in real trouble if you don’t announce it.
I wasn’t even talking about outliers in the data-breaking sense there, though. I really just meant that there must have been a lot of variation because that’s not as big a difference as I was expecting, based on old stories. There’s a few standard ways to measure that, actually an infinite series, but the two you often focus on for “outliers” in this sense are variance (literally just called that) and kurtosis. The higher order ones become increasingly nitpicky.