Polling Reporting 101

It’s been too long, and I felt strongly enough about this one – how some of the latest survey results on Canadian opinion on the Afghanistan mission – to want to post almost immediately.

First, here’s how the Toronto Star handled the latest survey results issued by Angus Reid:

“With the body of another Canadian soldier killed in Afghanistan due to arrive home tomorrow, the majority of Canadians are calling for an early troop withdrawal from the war-torn country …. An online survey of 1,052 Canadians by Angus Reid Strategies, conducted Dec. 19 and 20, shows 53 per cent of those polled believe Canada’s troops should be withdrawn before the February 2009 deadline.”

I know it may seem like a minor thing, but according to the Angus Reid release (.pdf), and as is mentioned in the article, the margin of error is +/- 3.1 per cent, 19 times out of 20.

This means that with a sample of this size, compared to mathematical predictions of what the results would be if EVERY Canadian was polled, the REAL number here could be as high as 56 per cent, or as low as 50. If that’s the case, wouldn’t it be fairer to say that “approximately half of those responding to an online poll” said x?

Rant, out.

Leave a Reply

Please log in using one of these methods to post your comment:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s