Iraq Poll: Note on Methodology
March 17, 2008 — -- This survey was conducted for ABC News, the BBC, ARD and NHK by D3 Systems of Vienna, Va., and KA Research Ltd. of Istanbul, Turkey. Interviews were conducted in person, in Arabic or Kurdish, among a random national sample of 2,228 Iraqis aged 18 and up from Feb. 12 to 20, 2008.
Four-hundred-sixty-one sampling points were distributed proportionate to population size in each of Iraq's 18 provinces, then in all 102 districts within the provinces, then by simple random sampling among Iraq's nearly 11,000 villages or neighborhoods, with urban/rural stratification at each stage.
Maps or grids were used to select random starting points within each sampling point, with household selection by random route/random interval and within-household selection by the "next-birthday" method. An average of five interviews were conducted per sampling point. Seven of the 461 sampling points were inaccessible for security reasons and were substituted with randomly selected replacements.
Interviews were conducted by 116 trained Iraqi interviewers with 31 supervisors. Fifty-seven percent of interviews were supervised or reviewed by supervisors – 34 percent by direct observation, 7 percent by revisits and 16 percent by phone. All questionnaires were subject to further quality-control checks.
In addition to the national sample, oversamples were drawn in Anbar province, Sadr City, Basra city, Kirkuk city and Mosul to allow for more reliable analysis in those areas. Population data came from 2005 estimates by the Iraq Ministry of Planning. The sample was weighted by sex, age, education, urban/rural status and population of province.
The survey had a contact rate of 92 percent and a cooperation rate of 65 percent for a net response rate of 60 percent. Including an estimated design effect of 1.52, the results have a margin of sampling error of 2.5 percentage points at the 95 percent confidence level.
SUNNI/SHIITE – Given the attitudinal differences between Shiite and Sunni Arabs in Iraq, there's interest in the relative sizes of these two groups. We find no official Iraqi estimate of the country's Sunni vs. Shiite Arab populations and no authoritative source of empirical data on the subject.
The most commonly cited estimate is an unsourced reference in the CIA World Factbook saying that 60-65 percent of Iraqis are Shiite Muslims, 15-20 percent Kurds and three percent non-Muslims. Though not explicitly stated, that leaves room for 12 to 22 percent Sunni Arabs.
This estimate may be derived from a 1988 book, "Iraq: a Country Study" produced by the Federal Research Division, Library of Congress. This book (pp. 80-81) characterizes data on ethnicity and religious doctrine in Iraq as "not absolutely reliable." It says, "Officially the government sets the number of Shias at 55 percent. In the 1980s knowledgeable observers began to question this figure, regarding it as low. …a more reasonable estimate of their number would seem to be between 60 and 65 percent." It adds, "…the Sunni Arabs…constitute a decided minority of only about 13 percent..."
These data also are unsourced. The 60-65 percent Shiite estimate matches that in the CIA World Factbook; the 13 percent Sunni Arab estimate compares to the World Factbook's unstated range of 12 to 22 percent.
Data from recent random-sample surveys, including the last three sponsored by ABC News with media partners, contrast with these unsourced estimates. This survey puts Iraq's population at 51 percent Shiite Arab, 30 percent Sunni Arab, 15 percent Kurdish and 4 percent other. The previous surveys were similar; in aggregate, 49 percent Shiite Arab, 33 percent Sunni Arab, 15 percent Kurdish and 4 percent other.
These three surveys comprise more than 6,600 interviews from 1,376 sampling points, a large sample with an unusual level of geographical coverage.
Iraq surveys from other sources are difficult to compare; some ask religious doctrine different ways, often reporting significant numbers of Muslims of unspecified doctrine; some use different weights, including weighting to a predetermined assumption of distribution by religious doctrine. In the absence of other persuasive empirical data, this poll did not weight Iraqis' religious doctrine to any assumed target.