News for hackers. Stuff that matters.

gridland

Re:Causal inference as a blind spot of data scientists on Sunday October 15, 2023 @02:27PM (#37892091)
just use propensity scores + ipw and you have the same thing as a rct. :)
Re:Facebook Shadow Profiles [pdf] on Friday February 18, 2022 @08:44PM (#30393644)
I work in advertising. The death of cookies is a huge annoyance to the industry. you are 100% correct that gclid or fbclid are just a means to store "the cookie" in plain text in the url string. All the big programmatic media platforms do it too now (The Trade Desk, Yahoo, etc).
That's cool. I'm a heavy R user and was like ???. RMarkdown is a game changer. Thanks for doing that and this.