Page tools: Print Page Print All | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
SURVEY METHODOLOGY
The sample was therefore spread across the States and Territories in order to produces estimates that have a relative standard error (RSE) of no greater than 10% for characteristics that are relatively common in the national population, say that at least 10% of the population would possess. Private dwellings included in the survey in each State and Territory were selected at random using a stratified, multi-stage cluster sample design. This sample included only private dwellings from the geographic areas covered by the survey. Each State and Territory of Australia was divided into geographic regions and then into smaller areas known as Collection Districts (CDs), the basic unit of enumeration in the Population Census. CDs were then divided into strata according to their geographic region (metropolitan and non-metropolitan), and the required number of CDs were randomly selected. All usual residents of the dwelling aged 15 years and over were asked to participate in the survey. The initial sample for the survey consisted of 18,500 dwellings. To enable an acceptable level of data accuracy and reliability to be achieved after allowing for sample loss (through factors such as vacant dwellings inadvertently selected in the sample, non-contacts and persons out of scope and coverage), the sample size was designed to achieve an expected fully responding response rate of 13,379 households, or 83%, after sample loss. SAMPLE ACHIEVED AND RESPONSE RATES When enumeration commenced, some dwellings selected for inclusion in the sample were found to have no possibility of delivering a survey response. Collectively these are referred to as sample loss, and comprise the following groups:
About 16,000 households remained in the survey after initial sample loss of approximately 2,300 households. After the survey was enumerated, households were categorised as responding or non-responding. Responding households are either fully or partially responding, depending on whether all persons in the household participated in the survey. Non-responding households include households affected by death or illness of a household member and households in which all the person(s) in the household did not respond because they could not be contacted, had language problems or refused to participate. The final number of fully responding households in SEARS 2007 was 13,736. Due to separate weighting being used for persons and households in SEARS 2007, data available from fully responding persons within a partially responding household were included in the published estimates for persons in SEARS 2007, covering 26,972 persons. The final response rate after sample loss was 85%. The following table shows the number of fully responding households and persons achieved for each State and Territory, by capital city/balance of State:
DATA COLLECTION Survey development Broad user consultation was undertaken during June and July 2005. A discussion paper was used as the key instrument in obtaining feedback and input from users for the development of the survey. Cognitive testing was carried out for questions designed for the new work and caring topic. Testing of the survey was also carried out to investigate respondent reaction and to ensure the effectiveness of interviewing procedures and instructions. Two trials were conducted:
These tests were used to:
Primary Approach Letter Selected households were initially approached by mail via a Primary Approach Letter (PAL), informing residents of their selection for the survey and advising them that an interviewer would call to arrange a suitable time to conduct the survey interview. A brochure providing a guarantee of confidentiality and some background information on the survey and the interview process was included with the PAL. Interviewers Interviewers for the survey were recruited from a pool of ABS interviewers, with previous experience on ABS household surveys and ABS training. All phases of training emphasised that a sound understanding of the survey concepts, definitions and procedures was necessary to ensure a standard approach was employed by all interviewers involved in the survey. As well as two days training, each interviewer was provided with written instructions detailing the procedures they were required to follow. Computer Assisted Interview The interview was designed to be administered using standard ABS procedures for conducting interviewer surveys with a responsible adult within the household to obtain valid and reliable results. The interview questionnaire concentrated on demographic and socio-economic information about each household person in on scope to identify population groups. To ensure consistency of approach, interviewers were instructed to ask the interview questions exactly as worded in the questionnaire. The interview included questions relating to ethnicity, education, labour force status, income, child care, age, superannuation, retirement and disability. A Computer Assisted Interview was undertaken by all persons aged 15 and over within the household, after an adult resident provided information relating to the household, and the first parent within the first family provided information relating to child care arrangements. Paper versions of the Computer Assisted Interview and prompt cards used in the survey are available in pdf format on the ABS website <www.abs.gov.au>. Requesting data from a superannuation fund During a face to face interview, respondents were asked to report the total number of accounts they had, and then the contribution and account balance information for up to their three main superannuation accounts, which accounted for 96.8% of the total number of accounts reported by respondents. For each of these three main accounts, respondents were asked the name of the fund (from which the fund type and benefit structure were derived), who (if anyone) currently contributed to that account, the amounts being contributed, and the amount of superannuation accrued (the superannuation account balance). To ensure the quality of data collected, survey respondents were asked to refer to relevant superannuation statements to report contribution and balance amounts. Respondents who were unable to refer to a current superannuation statement were advised that they could, should they choose to, authorise their superannuation fund to provide the information directly to the ABS on behalf of their member. Document Selection These documents will be presented in a new window.
|