chapter 2 review #308
chapter 2 review #308
Conversation
|
One question though: can we time-order that example DAG throughout? I know that's something we want to emphasize later on (and that's a good practice!) but I don't have enough ggdag-fu to make it look good for this example |
There was a problem hiding this comment.
Made some small changes, but a big one is that I reverted to group_by().
I also have a list of stylistic consistency decisions I am going to post as an issue so we can all be on the same page about them. I'd rather make those types of decisions comprehensively rather than as a suggestion on a PR
chapters/02-whole-game.qmd
Outdated
| @@ -410,7 +410,7 @@ In this example, we'll focus on weighting. | |||
| In particular, we'll compute the inverse probability weight for the **average treatment effect (ATE)**. | |||
| The ATE represents a particular causal question: what if *everyone* in the study used bed nets vs. what if *no one* in the study used bed nets? | |||
|
|
|||
| To calculate the ATE, we'll use the broom and propensity packages. | |||
| To calculate the ATE, we'll use the {[broom](https://broom.tidymodels.org/)} and {[propensity](https://github.com/r-causal/propensity)} packages. | |||
There was a problem hiding this comment.
I recently discovered that if you do `{pkgname}` in Quarto, this will happen automatically
|
Oh, re: time-ordering, you already made this suggestions and we decided to keep it as is because that is Andrew's DAG. That said, I'll file an issue because I'm going to make some improvements to the time-ordering algorithm that might make this easier to do automatically for a DAG like this. So we can re-explore soon |
mostly light copy edits