@tiki77747 i found this data set on the UCI repository, giving it as an option to my students to do regression on. is there any sort of relationships you'd be interested in seeing based on the variables? https://archive.ics.uci.edu/ml/datasets/SkillCraft1+Master+Table+Dataset …
-
damn, it's sort of strange that there are so many apm-related variables in this dataset, but aren't things like average game length, average bases taken, average expansion timing, chosen race, etc...
ANYWAY, i feel like it'd be cool to regress league on all the different measures of apm (e.g. apm, select by hotkeys, number of PACs, etc). it'd also be cool to see if some of those variables have larger effect sizes if you restrict league
-
-
e.g. if you restrict the set to just bronze-plat players, apm-related variables might be less predictive of league than if you restrict it to just diamond-pro
-
using TotalMapExplored as a response variable could be pretty cool too, my guess is that if you regressed it on the various apm-based variables and league, league would have a stronger effect than any apm metric
- Show replies
New conversation -
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.