Forensic Polling Analysis
Bad pollsters give the market research industry a bad name, so it is encouraging when smart people figure out clever ways of ratting them out. What is a bad pollster? One who makes up data to support an agenda, or who asks biased questions to get preferred answers. The only good reason for doing research or public opinion polling is to learn or share something new. All else is suspect.
Two researchers recently came up with methods of testing whether polling data is legitimate in a case where a research firm is accused of falsifying publicly released data. The researchers examined the last digit of the numbers released by the polling firm, and calculated the probability of seeing these digits in their specific combinations and frequencies if the polls were legitimate. It was an ingenious way of using sophisticated statistical methods to examine data where the accused firm refused to disclose details about its methods. The New York Times calls it “forensic polling analysis” and notes that in this case, the odds suggest that the polling data were fraudulent.
There are a number of leading industry organizations that have outlined ethical guidelines and principles of disclosure for survey research, including:
- AAPOR, the American Association of Public Opinion Research
- NCPP, the National Council on Public Polls
- CASRO, the Council of American Survey Research Organizations
Versta Research believes these guidelines are important to the health and integrity of research. We adhere to them and encourage our clients to do so as well. If you are unsure about your ethical obligations when releasing polling data to the public, give us a call and we can help you make sense of the guidelines.
—Joe Hopper, Ph.D.