1) There is something green about "quant" @Michael_Spagat and this paper
(cont)https://twitter.com/sapinker/status/1029092945088131072 …
-
-
Further excludes deaths under the Soviet Union, Maoist China, Pol Pot, et al. Does it not?
-
Amazing what liberty you can take with “statistics”
End of conversation
New conversation -
-
-
Hi. Of course, it would be great to do similar analyses on other concepts of war deaths. However, the only data sets I'm aware that are really useable to analyze war sizes over the last two centuries are battle deaths datasets.
-
The reason for this is that battle deaths are basically the lowest common denominator of information about war deaths that can be extracted with some degree of consistency, hence comparability, over all wars going way back in time.
-
Tweet unavailable
-
However, check out the huge pdf of documentation of their coding decisions. Peruse it for just 15 minutes and it should become clear just how how fragmentary the record is and how much judgment must be brought to bear to code the data.
-
Unfortunately, there is not a long history of tracking tracking war death numbers closely over two centuries. It's not at all simple to pull out two centuries worth of data on any concept of war deaths that you like.
-
Tweet unavailable
-
But for the foreseeable future, and maybe always, it will be hard to do anything other than to be aware of weaknesses in the data and to make caveats about what can be concluded from flawed data.
- 1 more reply
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.