[ SECRET POST #4193 ]

[case]

⌈ Secret Post #4193 ⌋

Warning: Some secrets are NOT worksafe and may contain SPOILERS.

01.



__________________________________________________



02.


__________________________________________________



03.


__________________________________________________



04.


__________________________________________________



05.


__________________________________________________



06.


__________________________________________________



07.


__________________________________________________



08. [repeat]


__________________________________________________



09.


__________________________________________________



10.



__________________________________________________



11.


__________________________________________________



12.



__________________________________________________



13.


__________________________________________________



14.









Notes:

Secrets Left to Post: 02 pages, 35 secrets from Secret Submission Post #600.
Secrets Not Posted: [ 0 - broken links ], [ 0 - not!secrets ], [ 0 - not!fandom ], [ 0 - too big ], [ 0 - repeat ].
Current Secret Submissions Post: here.
Suggestions, comments, and concerns should go here.

Comments

Re: Justice Kennedy is retiring

[(Anonymous)]

It's not at all enormous! I mean, think about it - if you roll a six-sided dice, there's a 1/3 chance that it'll come up with a 1 or a 2. Flipping a coin and having it come up heads twice in a row is actually less likely than 35%. And you wouldn't actually be shocked if either of those things happened, because they're well within the normal course of events.

He was a definite underdog, especially in the context of a presidential race, but 35% chances do happen, all the time. Unlikelier things happen all the time.

Re: Justice Kennedy is retiring

[(Anonymous)]

I mean, I'm looking at this data...

https://www.realclearpolitics.com/epolls/latest_polls/president/

...and it just seems like there were some issues with the polling, considering the actual outcome.

Re: Justice Kennedy is retiring

[(Anonymous)]

So there's several different things going on here?

I've been talking about statistical models for using poll data to estimate election outcomes - in particular, the 538 model for doing so, which gave roughly a 35% chance of Trump winning. And the nice thing about these models is that they do much of the work of collating and combining all the individual polls for us.

Raw poll data is much more specific and dependent on context to make use of. So, for instance, in this case, the polls that you're linking to are national polls. And... Clinton won the national popular vote. By about 2 points. So say the aggregate national poll put her about 3 points ahead, that would actually be fairly accurate.

The problem is that the election isn't won based on the national popular vote. It's based on state polls. And the thing with state polls is that they were very light on the ground - there just weren't a lot of good state-level polls being run in 2016, and this was particularly the case in much of the Upper Midwestern states like Wisconsin that Trump ended up winning. IIRC, this was one of the underlying reason for the 538 model giving him a 35% chance despite Clinton having a lead in the national vote - there was so much uncertainty on the state level, and those states gave Trump a path to electoral college victory. And that's what ended up happening - the race was tighter in those states than Clinton's campaign thought, and independents there broke late for Trump (probably based, in part, on the Comey letter).