Wednesday 27th November 2024, 13:30–17:00 (Australia/Melbourne), Sutherland Room
Traditional methods for making estimates from surveys rely on random (probability) samples and high response rates. As the costs of such surveys increase and as response rates decrease, the principles on which traditional methods are based are becoming harder to justify for samples for which the selection and response mechanisms are unknown (or unknowable). A range of statistical techniques have been developed for these situations, to try and model the selection mechanisms and enable estimates and inferences with respect to the target population.
This workshop will give practical advice and examples on design, weighting and estimation for contemporary surveys that do not meet traditional probability methods assumptions. Topics covered will include the following:
* Design considerations including sample composition, questionnaire items, data quality and benchmarks;
* Methods for estimating base weights, making use of a probability reference sample if one is available;
* Calibration to benchmarks; and
* Bias and variance assessment.
Andrew has almost 20 years of experience as a statistician and quantitative researcher, with expertise in survey research, analysis and reporting. His interests and capabilities include cross-sectional and longitudinal surveys, survey weighting and estimation, psychometrics and small area methods. He is currently Principal Statistician at The Social Research Centre, and an Accredited Statistician and full member of the Statistical Society of Australia.
Sam is a statistician at the Social Research Centre, with a focus on survey methodology and statistical modelling. He specialises in survey weighting and sample design, with extensive experience in Bayesian inference and complex survey weighting. Regular contributions to SRC projects include sample design and allocation, weighting and calibration of probability and non-probability surveys, bias and non-response analysis, and more. Sam’s recent research in survey methodology includes investigations into calibration and blending, panel conditioning, satisficing, and Bayesian small area estimation. He has presented research in Australia and overseas at the European Survey Research Association conference.