From Rob Salmond at Polity, this post on an interesting graph.
Here’s a pretty astounding graphic from the US about cellphone vs landline use, via Anzalone Lizst Grove Research:
The US is a few years ahead of New Zealand on mobile adoption and decoupling from landlines, but I think within 5 years we will see these kinds of proportions in New Zealand. This will make current pollsters’ policies of refusing to call cell phones hugely problematic – they will cut out almost half the population. No amount to weighting can reliably undo a sampling frame that unbalanced.
I know some pollsters are trying out online panels as a way to get the cell phone only population without the expense of talking to lots of cell phones. That is an innovative approach, and worth exploring. The sampling comparisons would need to be super robust, though, for it to be a long term solution.
lprent: Geographical variations probably already make this already the case in parts of Auckland. In the leadup to the 2011 election, there were electorates in South Auckland that had less than 50% of households with listed landlines. The Auckland isthmus had electorates with less than 60%. Whereas the North Shore electorates were largely over 75%. By contrast, some South Island rural electorates had close to 90%.
I’ve also observed a distinct age variant about what households have listed landlines. You’d have to argue pretty hard and with a lot of evidence to convince me that there isn’t a set of societal differential already strongly in play in NZ already distorting the polls without systematic cell coverage.