Building a probability-based online panel: Life in Australia™

Abstract

Life in Australia™ was created to provide Australian researchers, policy makers, academics and businesses with access to a scientifically sampled cross-section of Australian resident adults at a lower cost than telephone surveys. Panellists were recruited using dual-frame landline and mobile random digit dialling. The majority of panellists choose to complete questionnaires online. Representation of the offline population is ensured by interviewing by telephone those panellists who cannot or will not complete questionnaires online. Surveys are conducted about once a month, covering a variety of topics, most with a public opinion or health focus. Full panel waves yield 2000 or more completed surveys. Panellists are offered a small incentive for completing surveys, which they can choose to donate to a charity instead. This paper describes how Life in Australia™ was built and maintained before the first panel refreshment in June 2018. We document the qualitative pretesting used to inform the development of recruitment and enrolment communications materials, and the pilot tests used to assess alternative recruitment approaches and the comparative effectiveness of these approaches. The methods used for the main recruitment effort are detailed, together with various outcome rates. The operation of the panel after recruitment is also described. We assess the performance of the panel compared with other probability surveys and nonprobability online access panels, and against benchmarks from high-quality sources. Finally, we assess Life in Australia™ from a total survey error perspective.