Wondering how many people in the United States have a smartphone? If you poll 20 people on the street, your survey won’t be representative of the entire American population. But if you just want to ...

One possible explanation for the variability in estimates across the different nonprobability samples is the range of methods that online sample vendors employ. They differ on recruitment, weighting ...

The data in this report are based on two independent survey administrations with the same randomly selected, nationally representative group of respondents. The first is the center’s largest survey on ...

Targeting matters most. Surveying the wrong audience can lead to misleading data and poor decisions, even if the questions themselves are solid. Weighting shapes reality. Overrepresenting certain ...