Fandom data viz

[redfiona99]

I always liked "Cradle of our Renaissance" (https://archiveofourown.org/works/26618860), and right now I like it because it's the first gen fic to cross the 1000 hit boundary since I started doing the Kaplan Meier figures properly.







The proper one meanwhile looks like a proper K-M diagram.



The other thing is that this means I can finally do some number crunching on the properly done one.

Done properly, and covering fic I've posted in the past 7 years, there is no statistical difference in the chance of shippy and non-shippy fics reaching 1000 hits (p = 0.090833).

Comments

[greenwoodside]

I am in slightly envious awe of your data visualisation and statistics skills.

This post stood out while I was browsing because the data ran against my expectations – I guess for years I've been assuming that shippy fic would get more hits than genfic by lots a statistically significant margin of difference?

[redfiona99]

I will try to dig out the really nice "how to do this in Excel" explainer I found when I started this because they are a lot easier than they look.

That question was more or less why I started this, or rather I wanted to find a non-morbid set of data I could learn how to do Kaplan-Meiers with, and I had mine to hand and it seemed like a reasonable question. My expectation was similar, but I knew a few of my highest hitters were gen fics. 3 data points in the over bucket is not a lot to base anything on but it's a start.