This fact makes a mockery of the claim their methodology is based on science.
They get information.
The classic standard is that with a 1500 response (that is all of those 1500 have answered EVERY question and a goodly number have been called back to verify their responses) you have a plus or minus three percent margin of error in the best possible case scenario. That means that your sample actually represents the population you intend (presumably, but not necessarily ‘likely”, or “undecided” voters’. The math behind that is pretty provable and verifiable; if you have a hundred thousand, or a million or a billion jelly beans *IF* your sample is representative of the whole THEN a sample of 1500 is the point of diminishing returns, you would have to have a MUCH larger survey to gain even a fraction of accuracy... Since a ‘perfect’ sample is pretty much impossible to take (or more accurately it is impossible to KNOW you’ve taken a perfect sample), interpreting the data, gauging it’s accuracy well enough to know where to throw the money, that is the skill. That’s what makes folks like Rove, Atwater, Morris and such the influences they are or were (actually it was as often wonks on their staffs).
By definition, if they got “no information” from them, they were not part of the sample. IF they got incomplete demographic data then there are the techniques I’ve alluded to above to turn the noise and static into the daily racing form :-)
The people who get paid the big bucks are the ones who can extract the information from the noise.