World Values Survey 2004, Wave 4

Sample size: 2325

For the purpose of this research, population frame was defined as all adult citizens (18 years and more) who lived in Iraqi urban and rural areas. Iraq 1997 census data used as the framework to draw the sample. The sample consists of 2700 respondents in 16 provinces (governorates) out of 18 Iraqi provinces. The number of cases to be included for each governorate was determined by considering:

1. each governorates population as a percentage of the overall population,
2. the number of cases necessary to make valid regional comparisons, and
3. rural area population as a percentage of the governorate population.

Two Iraqi provinces, Mosul and Duhuk, had been excluded from the sample. The bad security situation in Mosul made it very risky to conduct any interview there. Duhuk security authorities prevented the interviewers from working in that province. The interviews proportion of Duhuk allocated to Erbil and Sulaimania, which are Kurdish provinces also, to reserve the Iraqi ethnicity proportions. Mosul share of interviews allocated to other three Sunni provinces and cities (Tikreet,Rumadi and three of Baghdad neighbourhood) to reserve the Iraqi sects representations. A multi-stage probability-based sample was drawn, utilizing residential listings from Iraqs 1997 Population Census(data has been attached). Six sampling stages have been deployed. First, number of interviews has been distributed among census districts (Qada) proportionally. Second, each Qada consist of number of census sub districts called (Nahia) which received its share of interviewsproportionally, also. Nahias, in turn, consist of many blocks. At the third stage, blocks regarded as the primary sampling units (PSU) in the urban areas, with 135 PSUs being selected using probabilityproportional-to-size procedures. 20 interviews have been conducted in each block. These 20 interviews were distributed among 4 streets (Zukak according to census wording) in the fourth stage. These streets selected by using simple random method. Because more than seven years have been gone since the date of the census, many variables could happened for the residential list in each street, that's why every interviewer has been asked to draw on a spot map for the households that were located in the street he\she suppose to work in. In the fifth stage, each interviewer select, randomly, 5 households in the street depending on random tables. Finally, within each selected household, one respondent was randomly selected using the last birthday method. Because most old Iraqi citizens doesnt knows their exact birthday, a list of random birth days used by every interviewer to replace the birth day of every old citizen who dont know his/her birth day. Due to the inaccuracy of the addresses in the rural areas, interviewers have been trained on how to use simple rules in choosing the household which should be interviewed. Same thing practiced on the urban Kurdistan provinces which did not covered by the 1997 national census. Standard rules have been followed to choose blocks, streets and households. The rule of choosing the respondent is same in all 2700 interviews.

Remarks about sampling:

The margin of error was calculated in order to

1. incorporate the clustering effects of multistage sample design, and
2. to provide 95% confidence level. Although the overall margin of error is estimated at ±2.3% (n=2325), the margin of error varies across the 16 governorates included in the sample.