How the poll on Vietnam was conducted

The Associated Press-GfK Vietnam Poll on the attitudes of Vietnamese was conducted by GfK Roper Public Affairs & Media from Feb. 23 to March 25, 2010. It was based on face-to-face interviews in the Vietnamese language with a random sample of 1,600 people age 18 and older.

In a technique called area probability sampling, 48 cities, towns and other locations were selected to reflect the country's population distribution between urban and rural regions.

Next, a total of 100 smaller areas — 60 urban and 40 rural — were selected from within the initial 48 communities. Remote areas without drivable roads and some minority ethnic groups with limited command of the Vietnamese language were excluded, meaning that about 10 percent of the population was omitted.

Interviewers were assigned random routes within each of the 100 areas. They selected households to interview using a sequential pattern.

Within each household chosen, interviewers randomly selected one adult. If the selected adult was not there they revisited the home. If that adult was not present the second time, they moved on to a different home.

As is done routinely in surveys, results were weighted, or adjusted, to ensure that responses accurately reflect the population's composition. That included Vietnam's mix by age, gender, its six regions and its mix of urban and rural communities.

No more than one time in 20 should chance variations in the sample cause the results to vary by more than plus or minus 3.2 percentage points from the answers that would be obtained if all adults in Vietnam were polled.

There are other sources of potential error in polls, including the wording and order of questions.

The questions and results for this poll are available at http://www.ap-gfkpoll.com.