Stephen is Managing Director of Prescience Research, a Melbourne-based marketing research and data modelling consultancy. He has had a 30 year career in marketing research and management consulting. Stephen has experience on key projects for major enterprises in services, FMCG, information technology sectors, and government departments and is well known for his thoughtful use of mathematical and statistical models as a bridge to better decision making. He has applied these methods in a variety of decision areas including customer service and loyalty studies, advertising response, brand health tracking and time series analysis, customer segmentation, data mining and demand estimation models including choice modelling, conjoint and simulated test markets.
He has received post-graduate training in sophisticated fields such as choice modelling, marketing models, general linear models and structural equation modelling. Stephen has also lectured l on Marketing Models and Market Research at Monash University, and written articles on Statistics and Marketing support software for MacNews. During 2004-16 Stephen has conducted key AMSRS statistics one day courses as well as webinars for the society. Stephen served on the AMSRS Professional Development Committee from 2011-2016, and as chair 2014-2016. Stephen has an honours degree in Applied Science from University of Melbourne, a Marketing degree from Monash University, and is a Qualified Practising Market Researcher (QPMR).
Co-Presenters: Darren Pennay
The increase costs associated with mounting high quality CATI surveys and the rapid decline in response rates for such surveys has seen many in our industry turn to non-probability online panels. The advantages of these panels include reduced costs (relative to other modes of data collection), quick turnaround times, respondent convenience, reduced social desirability bias due to the self-completion mode of collection, the ability to target hard to reach populations, multimedia functionality and computerised questionnaires. However, what about the quality?
This paper presents the international research and now some Australian research showing that surveys administered to members of non-probability panels are considerably more biased (generally more than double the bias) and more variable than surveys administered using probabilistic sampling methods. In fact, the estimates produced from some non-probability samples are sometimes dangerously inaccurate. However, this paper doesn’t just shine a light on a problem but presents the latest Australian and international research exploring ways to reduce this bias and improve the inferences which can be made from non-probability panels. In so doing we look at techniques such as model-based design weights, sample blending and calibration. These methods are equally applicable to both market and social researchers.