Central Survey Unit
ABOUT US NEWS ROOM SURVEYS PUBLICATIONS LINKS

Surveys colour code
HOME
CONTACT US
SITE INDEX
Surveys header
Surveys image NI Statistics and Research Agency

current surveys

archived surveys

home > surveys > Community Attitudes Survey   

Community Attitudes Survey

Methodology

Questionnaire

The content of the CAS questionnaire is agreed on a yearly basis in consultation with the clients for the survey. While it remains largely the same from year to year, questions may be added, removed or the wording amended. The content for each year since 1992/93 can be found in the questionnaire section of this website.

Sample

CAS is a household survey that is designed to yield a representative sample of all adults aged 16 or over living in Northern Ireland. The sample of 2,400 addresses is drawn at random from the Valuation and Lands Agency (VLA) property database. This is the most up-to-date listing of private households and is made available to NISRA for research purposes. People living in institutions (though not in private households in such institutions) are excluded from the sample. CAS is designed to yield a representative sample of all adults aged 16 or over living in Northern Ireland.

Selected Respondent

One person in each household is selected at random to participate in the survey. Interviewers call at each address and identify the number of households resident at the address. Where there is more than one household at the address, one will be selected. The interviewers then list on the computer all members of the household who are eligible for inclusion in the survey (ie all persons aged 16 or over and living in the household). From this listing of eligible adults, one person (the selected respondent) is selected at random by the computer. The selected respondent is then asked to complete the interview. The interviewer cannot accept a replacement for this person should they refuse to participate, or if no contact can be made with them.

Fieldwork

Addresses are issued to a panel of interviewers on a monthly basis between January and December of each year. The issued sample accounts for the possibility of non eligible properties on the sample list and assumes a response rate of 65% to achieve a minimum of 1400 achieved interviews during the field period.

Weighting

Selecting only one individual for interview at each sampled address means that the probability of selection for the survey is inversely related to the size of the household. In other words, individuals living in large households have a lower chance of being included in the sample than individuals in small households.

Before analysis the data are weighted in relation to the number of eligible adults at the address, derived from the details of household structure recorded by interviewers on the questionnaire. The weighting process adjusts the results to those that would have been achieved if the sample had been drawn as a simple random sample of adults rather than of addresses. The results produced from the survey are weighted in this way.

Full details of the survey methodology are available in the latest technical report.

 



   


[ home ] [ contact us ] [ site index ]     about us | news room | surveys | publications | links


© 2003 Central Survey Unit - Northern Ireland Statistics & Research Agency