It remains a mystery how Shitt Romney has been successful in the business world when he obviously has absolutely no clue on even the most basic concepts of Statistics. You can’t get accurate measurements of surveys when you self-select your “online” sample group(s). Results of probability can best be measured from RANDOM SAMPLING. You can’t make an accurate claim about the probability of results from a sample, when you in essence, have too much control over the group(s) being sampled. The results are as statistically genuine as a verdict handed down by a jury during a John Gotti trial. The excerpt below is from a online survey(conducted by The U.S.Chamber of Commerce) of self-selected small-business owners. I’ve only taken two undergraduate Statistics classes, and one at graduate level, so read and research the facts for yourselves. -Daryl-
Romney cites a recent online survey to support his claim that the law is a “job-killer.” The U.S. Chamber of Commerce conducted an online survey in late March and early April, and 1,339 executives at companies with fewer than 500 employees and revenues of less than $25 million participated. The chamber, which opposes the health care law and has run numerous TV adsattacking it, reported that 73 percent said the health care law is “an obstacle to growing their business and hiring more employees.”
That statistic was based on an online, opt-in survey of small-business executives. A press releasefrom the Chamber of Commerce about the survey carries a large caveat: “This online survey is not based on a probability sample and therefore no estimate of theoretical sampling error can be calculated.” In other words, the chamber can’t be sure it’s a representative sample of small-business executives.
Those kinds of surveys can be useful for marketing research purposes, said Scott Keeter, director of survey research at the Pew Research Center and the most recent past president of the American Association for Public Opinion Research. “But from the point of view of public policy decisions, they tend not to be given much credence.”
“The bottom line is that surveys that have self-selected samples don’t have any known relation to the target group [in this case small-business owners],” Keeter said. “As a result, it is difficult, if not impossible, to know what kind of weight to give this.”
- Do Google Surveys use Probability Sampling? #MRX #MRMW (lovestats.wordpress.com)