"comfortable making EV estimates" prompts this (possibly self-serving) hypothesis: one of the highest leverage things someone like me could work on would be tools to give many more humans access to bayesian modeling (eg, a "bayesian spreadsheet"), improving the EV of EV estimateshttps://twitter.com/juliagalef/status/984142820754649088 …
Replying to @kellan
Power just went out here so will have to answer at length later. EV = expected value; integrating value over all possible outcomes properly needs distribution-based modeling instead of point estimates. Spreadsheets currently don't encourage this, but one could be built to.
1:50 PM - 11 Apr 2018
0 replies
0 retweets
1 like
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.