|Page tools: Print Page Print All|
QUALITY DECLARATION - SUMMARY
The SDS was conducted throughout Australia from 31 January to 1 March 2016. Data was collected by trained ABS Interviewers who conducted computer–assisted telephone interviews with respondents who agreed to participate in the SDS. The data from the survey is being released approximately four months after the completion of enumeration in the form of a summary publication, containing a set of tables in spreadsheet format.
The second release of SDS, scheduled for early 2017, will include an analysis of the relationship between responses to the WG Short Set and disability data from the 2015 SDAC.
The sample for the SDS was taken from the household component of the 2015 SDAC, which included private dwellings and self-care units in retirement villages. Respondents who were a responsible adult in households that were enumerated in the 2015 SDAC between September and November 2015 were asked whether they would be willing to participate in a follow up survey. Those who agreed to participate and provided at least one valid phone number were included in the SDS sample. After sample loss and non-response, the final sample included 6,213 private dwellings.
Estimates in this publication are subject to sampling and non-sampling errors. Sampling error is the error associated with taking a sample of dwellings rather than going to all dwellings in Australia. In this publication the sampling error is measured by the relative standard error (RSE), the standard error expressed as a percentage of the estimate. Non-sampling errors can occur in any data collection, whether based on a sample or a full count such as a census. Sources of non-sampling error include non-response, errors in reporting by respondents or recording answers by Interviewers, and errors in coding or processing of data. Every effort is made to reduce the non–sampling error by careful design and testing of questions, training Interviewers, follow-up of respondents and quality control procedures throughout data processing.
Estimates and RSEs in this publication have been assessed to ensure the confidentiality of those individuals and dwellings contributing to the survey. A technique has been developed to randomly adjust each estimate prior to publication, based on the mathematical method of perturbation. These adjustments result in estimates being affected by a small introduced random error, sufficient to ensure the un-weighted units counted within the estimate remain confidential. In most cases, perturbation will have only a small impact on the estimate, while ensuring the information value of the published data as a whole is not impaired.
The SDS was a follow up survey to the 2015 SDAC. The SDAC and the SDS both provide measures of disability, however their purpose, concepts and collection methodologies are different so further analysis will assess their comparability. The first results from the 2015 SDAC were published in:
The SDS used the United Nations' endorsed WG Short Set of questions which have been asked in many countries. However, compared to other countries, the SDS used different data collection methods. ABS Interviewers conducted telephone interviews with respondents, while paper or face to face collection methods were often used in other countries. The respondent answered the WG questions on behalf of each person in the household aged five years or over, with each WG question being asked for all people in the household before proceeding to the next question.
This publication contains tables and some key findings to assist with the interpretation of the results of the survey. Detailed Explanatory notes, a Technical note on Data Quality and a Glossary are also included providing information on the terminology, classifications and other technical aspects associated with these statistics.
The tables contained in the Downloads tab of this publication are available on the ABS website, in spreadsheet format. The spreadsheet also presents relative standard errors (RSEs) relating to estimates and margins of error (MOE) for proportions for each publication table.
These documents will be presented in a new window.