Polling in the United States Historically, the Gallup Poll has used
opinion polling to measure and track the public's attitudes concerning
political,
social, and
economic issues, including sensitive or controversial subjects. The Gallup Poll division's results, analysis, and videos are published daily in the form of data-driven news. As of 2012, conducting polls generated approximately $10 million in the company's yearly financial losses; however, it provides the Gallup brand name visibility, which helps promote its corporate research.
Gallup Daily tracking methodology Until 2018, Gallup Daily tracking had two surveys: the Gallup U.S. Daily political and economic survey and the Gallup–Healthways Well-Being Index. For both surveys, Gallup conducted 500 interviews across the U.S. per day, 350 days out of the year, with 70% on cellphones and 30% on landlines (with 34% of the nation relying on cell phones only in 2012. Gallup Daily tracking methodology relied on live interviewers, dual-frame
random-digit-dial sampling (which included landline as well as cellular telephone phone sampling to reach those in cell phone-only households), and used a multi-call design to reach respondents not contacted on the initial attempt. The findings from Gallup's U.S. surveys were based on the organization's standard national telephone samples, consisting of list-assisted random-digit-dial (RDD) telephone samples using a proportionate,
stratified sampling design based on randomly generated phone numbers from all working phone exchanges (the first three numbers of a local phone number) plus unlisted phone numbers. Within each contacted household reached via landline, an interview was sought with an adult 18 years of age or older living in the household who would have the next birthday. Because cell phone numbers are typically associated with one individual rather than shared among several members of a household, Gallup did not use the same selection procedure for cell phone interviews. Gallup Daily tracking included interviews in Alaska and Hawaii, and Spanish-language interviews. When respondents to be interviewed were selected at random, every adult had an equal probability of falling into the sample. The typical sample size for a Gallup poll, either a traditional stand-alone poll or one night's interviewing from Gallup's Daily tracking, was 1,000 national adults, generating a
margin of error of ±4 percentage points. Gallup's Daily tracking process allowed Gallup analysts to aggregate larger groups of interviews for more detailed subgroup analysis, but the accuracy of the estimates derived only marginally improved with larger sample sizes. After Gallup collected and processed survey data, each respondent was assigned a weight so that the demographic characteristics of the total weighted sample of respondents matched the latest estimates of the demographic characteristics of the adult population available from the U.S. Census Bureau. Gallup weighted data to census estimates for gender, race, age, educational attainment, and region. The data were weighted daily by number of adults in a household and the respondents' reliance on cell phones to adjust for any disproportion in selection probabilities. The data were then weighted to compensate for nonrandom nonresponse, using targets from the U.S. Census Bureau for age, region, gender, education, Hispanic ethnicity, and race. The resulting sample represented an estimated 95% of all U.S. households.
Accuracy From 1936 to 2008, Gallup Polls correctly predicted the winner of the presidential election with the notable exceptions of the 1948
Thomas Dewey–
Harry S. Truman election, where nearly all pollsters predicted a Dewey victory (which also led to the infamous
Dewey Defeats Truman headline), and
1976, when they inaccurately projected a slim victory by
Gerald Ford over
Jimmy Carter. For the 2008 U.S. presidential election, Gallup correctly predicted the winner, but was rated 17th out of 23 polling organizations in terms of the precision of its pre-election polls relative to the final results. In 2012, Gallup incorrectly predicted that
Mitt Romney would win the
2012 U.S. presidential election. Gallup's final election survey had
Mitt Romney at 49% and
Barack Obama at 48%, compared to the final election results showing Obama with 51.1% to Romney's 47.2%. Poll analyst
Nate Silver found that Gallup's results were the least accurate of the 23 major polling firms Silver analyzed, having the highest incorrect average of being 7.2 points away from the final result. Following the results of the election, Gallup spent six months reviewing its methodology. In 2012, poll analyst Mark Blumenthal criticized Gallup for a slight but routine under-weighting of black and Hispanic Americans that led to an approximately 2% shift of support away from
Barack Obama. At the same time, Blumenthal commended Gallup for its "admirable commitment to transparency" and suggested that other polling firms disclose their raw data and methodologies. In 2013, the accuracy of Gallup polling on religious faith was questioned. Gallup's polling on religiosity in the U.S. has produced results somewhat different from other studies on religious issues, including a 2012 study by the
Pew Research Center, which found that those who lack a religious affiliation were a
fast-growing demographic group in the U.S. In 2016,
The Wall Street Journal published a comparison of Gallup's survey-based measurement of unemployment with the same estimate from the U.S. Bureau of Labor Statistics (BLS) from 2010 to 2016. The numbers almost exactly match, and the trend is highly correlated, despite a larger sample size from the BLS, suggesting Gallup's design and weighting methods generate estimates consistent with government agencies.
Gallup World Poll In 2005, Gallup began its World Poll, which continually surveys citizens in 160 countries, representing more than 98% of the world's adult population. The Gallup World Poll consists of more than 100 global questions as well as region-specific items. It includes the following global indexes: law and order, food and shelter, institutions and infrastructure, good jobs, wellbeing, and brain gain. Gallup also works with organizations, cities, governments, and countries to create custom items and indexes to gather information on specific topics of interest. Gallup additionally publishes other studies and results, such as its State of the Global Workplace report, Global Emotions report, and Rating World Leaders report.
Gallup World Poll methodology Gallup interviews approximately 1,000 residents per country. The target population is the entire civilian, non-institutionalized population, aged 15 and older. Gallup asks each respondent the survey questions in their own language to produce statistically comparable results. Gallup uses telephone surveys in countries where telephone coverage represents at least 80% of the population. Where telephone penetration is less than 80%, Gallup uses face-to-face interviewing.
Surveys on China Gallup is known for its public opinion surveys about China. Its latest survey, published in March 2023, stated that a record-low of 15% Americans have a favorable view of China, a metric it has been measuring since 1979. In early November 2023, Gallup announced that it had closed all operations in China, a country that it first entered in 1993. ==Gallup's Exceptional Workplace Awards==