Some recent statements about the state of political polling in Canada may be delightfully apocryphal to those who detest what pollsters do. But the problem is that the testimony doesn't square with the facts. What's especially discouraging is that many of these statements have been made by people who should know better.

One misstatement recently bandied about is that political polls in Canada aren't based on "true" random samples, so they are prone to error. Supposedly, this is our "dirty little secret."

This statement is completely ridiculous. Nobody in the world does true random samples for political research. And nobody has ever conducted a random sample for a political survey in Canada, ever. True random samples take too long, are too expensive and are overkill for the task at hand.

All pollsters in Canada do some form of cluster sampling. They always have. It's standard industry practice. The question to ask is: Have our polls suffered as a result? No. Canada's major pollsters almost always predict the results of elections within the margin of error, and when we haven't, it's not because of a problem with sampling.

We're not whistling past the graveyard on this. Response rates are indeed falling. But we are also coming up with new techniques to fill the gaps. Whether it is through online surveys, mobile-phone supplement samples or innovative weighting schemes, market researchers are constantly inventing new ways to create valid and reliable surveys.

This is because the multibilliondollar -and growing -marketresearch industry demands it. And, for the record, Ipsos-Reid is the largest market research company in Canada. And Ipsos-Reid is a division of the Ipsos, the world's second-largest survey research company.

Second, because the media doesn't pay commercial rates for political polls, research companies cut corners in terms of research quality. We can't speak for everybody on this, but at Ipsos-Reid we absolutely don't cut any corners on the surveys we release into the public domain. The same quality controls that we apply to our commercial research are applied to our political polling. This isn't a matter of money. When our name goes on a poll, it's our firm's reputation that's on the line. We expect that our responsible competitors take the same approach.

Canada's pollsters should remember that they perform an important public service. Our polls speak truth to power.

Not doing polls, or doing fewer of them, means that there will be no checks on bad polls (in this sense, the more polls the better), and that the political elites, including the media, will push their own distorted view of public opinion.

Some critics seem to have given up on this. We can assure you that Ipsos-Reid has not.

Darrell Bricker is CEO of Ipsos-Reid public affairs. John Wright is senior vice-president for the Canadian Public Affairs Division of Ipsos-Reid Canada