so, yes - the numbers pushed the brink. it looked like a trend. it really did.

but, they seem to be readjusting around a mean of about 16%, +/- 4.

this process simply isn't more precise than that.....

i mentioned that nanos had them consistently higher the whole time - 15ish when other people had them closer to 10. so, the lack of movement in his numbers is particularly instructive - they're running at about 16%, give or take, and have been the whole time. that's not high enough to be a serious factor in the election.

also, the fact that singh's numbers are climbing higher than the party's is more evidence of a wilder effect. so, that's my take on what's going on...

1) nik had them higher the whole time. he was right.
2) but, that means the movement was illusory - statistical fluctuation.
3) i've noticed a few times now that the ndp numbers seem to go up over long weekends, only to crash again after. this may be a phenomenon in sampling bias.
4) there's a wilder effect happening. for real.

https://secureservercdn.net/198.71.233.47/823.910.myftpupload.com/wp-content/uploads/2019/10/2019-1445-CTV-Globe-ELXN-2019-10-15.pdf

the liberals are supposed to do better than this