[drinkzima]

"Consequently, we filter our dataset down to only those companies that raised a seed round with AngelList, and those companies’ subsequent rounds of fundraising that we have information on"

Doesn't that mean the conclusions of this are based upon only companies that did a follow-on round, not companies that raised money in general? Of course there are seasoning effects, but throwing out all the companies that can't raise to conclude "Our model shows that at the seed stage investors would increase their expected return by broadly indexing into every credible deal".

If that was the case, the conclusion should be "our model shows that seed investments that receive follow on investment should be indexed to", but that isn't know at the time of the previous round. The discussion seems to ignore the huge bias of censoring as well, but I might be missing something and I didn't get through every word.

[mateo411]

Yes, I suspect there is some survivorship bias in this analysis.