Just wondering, do these polls reach people through social media or are they conducted as in the past, strictly by phone?
• Ballot tracking reflects only the first choice given by decided voters
• A national dual-frame (land+cell) random telephone survey is conducted nightly by Nanos Research throughout the campaign using live agents. Each evening a new group of 400 eligible voters are interviewed. The daily tracking figures are based on a three-day rolling sample comprised of 1,200 interviews. To update the tracking a new day of interviewing is added and the oldest day dropped. The margin of error for a survey of 1,077 decided voters is ±3.0 percentage points, 19 times out of 20.
• The margin of error for weekly surveys before Sept. 4 is ±3.1 percentage points, 19 times out of 20
This is way off topic, but if there are any statisticians out there, can you tell me why they phrase things like this. Is the margin of error +/- 3 or not .... if this happens to be the 20th time, what is the margin of error? Or is it completely unknown? 19/20 is 95% so why not just build that other 5% of uncertainty into the +/- 3.
It all seems a little hodge-podge.