Sample Design
The strict, probability-based sample design Gallup used to conduct this survey projects with scientific accuracy to all adults (aged 18 and older) residing in Iraq, with the exception of those residing in the governorates of Arbil and Dahuk*. All 3,444 interviews were conducted face-to-face, in the privacy of the respondent’s own home. For results based on this sample, one can say with 95% confidence that the maximum error attributable to sampling and other random effects is ±1.7 percentage points.
Interviewing was conducted during the period of March 22 through April 2, with the exception of the governorate of Sulaymaniyah, where interviewing extended until April 9, 2004. The cooperation rate was 98% -- that is, only 2% of those households we contacted refused to be interviewed. The average interview length was 70 minutes.
Interviewing was conducted in 350 separate locations across the country, encompassing both urban and rural sectors. Two-thirds of the interviews were conducted in areas classified as urban, and the remaining third in areas classified as rural.
Selection of the sample was done at the qadha administrative unit level, with a total of 350 primary sampling units (PSUs) selected on a strict, probability-proportional-to-size basis. An average of 10 interviews, one per household, was conducted in each of these locations.
A more detailed description of the selection process is as follows:
Each governorate (“mohafatha”) consists of multiple administrative units known as qadhas. The 16 governorates surveyed include a total of 93 qadhas, and interviewing was conducted in each of these during the course of this survey. Each qadha consists of multiple districts known as nahiya; there are a total of 223 nahiyas in the 16 surveyed governorates.
Each nahiya consists of multiple mahalas (neighborhoods) of varying population sizes. Gallup obtained the adult populations of each of these mahalas from a 2002 Central Statistical Office update, with the adult population defined as those born in 1986 or earlier. In collaboration with the Central Statistical Offices of Baghdad and Sulaymaniyah, these data enabled Gallup to assign the appropriate population weight for each of the mahalas into which a sampling point for our survey fell. There are a total of 2,443 mahalas in the 16 governorates surveyed.
Each mahala, in turn, is made up of blocks known as majals. Majals contain multiple, proximate housing units, often along the course of a given road or street (longer roads may stretch across multiple majals). Within our sampling frame, there are 116,314 majals exclusive of Sulaymaniyah, where the available census data extend only to the level of mahalas.
Once the number of PSUs to be allocated to a given qadha was determined, these were then assigned -- again, on a probability-based basis -- to specific nahiyas, mahalas, and majals within that qadha, with no more than one majal selected within any given mahala.
Interviewers were given all the relevant address details for each PSU. However, because the only available residential listings were based on a 1997 census, all residential listings had to be updated.
In addition, the available listings consisted solely of dwelling addresses, regardless of the number of independent families residing within a given housing unit. Therefore, we compiled separate listings identifying independent families, based on the criterion of their preparing or eating meals independently.
In those instances in which more than 10 independent families resided in a given, selected majal, a random selection table was used to select which families would be interviewed.
Finally, within each selected household, the specific adult to be interviewed was selected by the Kish method. This research procedure, designed to ensure proper representation of all age groups and both genders in the sample, involves first recording the ages and sex of each of a selected household's adults on a grid. The respondent to be interviewed is then selected according to a prescribed systematic procedure.
*The three predominantly Kurdish governorates of Arbil, Dahuk, and Sulayminayah have their own administrative agencies that have been largely independent from those based in Baghdad for more than a decade. Because the Central Statistical Office of Arbil did not participate in this project, we were unable to interview in Arbil and Dahuk. Additional interviewing was therefore conducted in neighboring Sulaymaniyah, so that a total of 446 interviews -- 13.0% of our nationwide sample -- was conducted within this region. According to the latest available population estimates, these three governorates collectively account for 13.1% of Iraq’s total population (Sulaymaniyah: 6.3%, Arbil: 5.1%, Dahuk: 1.7%).
