No. The sample sizes used mean that this is all noise on the graph.
-
-
I looked at the partner count sample for basically this same group on Monday and it was decently large so I’m surprised the sexual frequency question is such a low N, unless it was a result of conditioning on marriage.
1 reply 0 retweets 7 likes -
There’s not close to the power you need to meaningfully detect an interaction. I mean even if you didn’t know anything about the size of the GSS it’s obvious from getting 0% celibacy for women.
1 reply 0 retweets 7 likes -
What’s the interaction? I mean my thread about this was skeptical about any appreciable movement in overall male sexual frequency and partner count. It seems possible that there’s been significant change in the number totally non-sexually active.
1 reply 0 retweets 3 likes -
This is implicitly trying to get at celibacy as a function of year, sex, and year x sex; there’s the interaction. Anything’s possible but people should basically not update at all from this graph
3 replies 0 retweets 3 likes -
I mean, what happens isn't we see the graph and radically change our understanding of the world to fit it
2 replies 0 retweets 14 likes -
The graph, like low N research more generally, is dangerous because if the people who view it see it fitting their priors, they feel encouraged that their view is evidence based.
1 reply 0 retweets 1 like -
Replying to @bechhof @alicemazzy and
if the gss is the most egregious example of low-n social science you’ve ever encountered i’ve got bad news for you
2 replies 0 retweets 9 likes -
Replying to @QuasLacrimas @bechhof and
yeah, just the idea that it's publicly reproducible and they probably didn't make the numbers up out of whole cloth is light years ahead of the competition
1 reply 0 retweets 4 likes -
Replying to @toad_spotted @bechhof and
“this is dangerous it might reinforce someone’s priors” is brilliant why didn’t the Stasi think of that?
1 reply 0 retweets 2 likes
“Comrade, we have reports of an invalid causal inference... please evacuate the library immediately”
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.