Thought Leader (VoPP Mag) Michele Levine

VoPP Mag
A marketing magazine for marketers, creative agencies, media buyers and printers.
The value of Paper and Print (VoPP) is an effectiveness campaign raising awareness of the power of paper, print and mail marketing in today's noisy communications world. VoPP is a unified voice for the paper, print and mail industry and supports members with quality marketing collateral, PR and media representation and target consumer research. VoPP is supported by the industry across the channels it represents. All commitment to promoting the effectiveness and environmental credentials of print marketing and media in the Australian and New Zealand markets whilst balancing the critical role of a multi-channel universe for all.
With over 30 years' experience as a researcher, CEO of Roy Morgan Research Michele Levine has led thousands of surveys, including many of the largest research projects ever undertaken in Australia, many of which continue to play a critically important part in shaping our society today.
Why is research so important in today's climate?
In today's fast-changing and increasingly digitised world, it's more important than ever to have accurate information about the forces that are driving consumers and influencing their thoughts, behaviour, preferences and consumption decisions.
Research is an indispensable part of the bedrock of understanding the different forces that drive consumer behaviour. Roy Morgan's understanding of the mind of the consumer delivers unique and valuable insights into what drives the average Australian. In addition to the consumer mindset, Roy Morgan has a strong focus on the economic pulse of Australia via several weekly, monthly and quarterly indicators. These indicators provide our clients with timely insights into how Australian consumers - and businesses - are dealing with the rapidly evolving macroeconomic environment and, what their feelings and opinions mean for driving future consumer behaviour across the economy.
So, why is research essential in today's climate? If you can't measure it, you can't manage it. And if you can't manage it, you can't fix it.
What statistical analysis tools and database software have you previously used? What are your favourites and why?
The pre-eminent statistical analysis tool we use is the ASTEROID software user interface. This is an easy-to-use tool with minimal experience and enables users, including ourselves and our clients, to interrogate the Roy Morgan Single Source consumer database, arguably the best consumer database of its kind in the world. Another favourite we use at Roy Morgan is Tableau which is an easy-to use statistical analysis tool that functions in an attractive user interface.
We predominantly use Tableau as a data analysis and visualisation tool in our day to-day work. The data fed into Tableau is prepared using Google Big Query. Although not strictly a statistical analysis tool, another favourite we use is Python programming language. Python's simplicity, versatility, rich ecosystem and active community make it a great tool for beginners and experts alike.
What are some best practices for data cleaning? What are the steps you take?
We put in place a number of checks to identify poor quality responses, seeking to eliminate what is known as speeding and pattern (also known as straight-lining). Parameters for such checks are specific to each survey, but for example, we seek to identify responses that have been completed too quickly (which indicates a lack of consideration for answers, and the likelihood that the respondent is completing answers at random), or where the respondent is using the same response continually. We will, for example, identify repeated and excessive use of the 'don't know' and 'prefer not to say' answer options, and remove them. We also oversample to allow headroom for the removal of problematic records while maintaining the required overall sample size - this is undertaken within a rigorous quality assurance process.
Describe your most complex data project from start to finish. What were the most difficult challenges, and how did you handle them?
Our most complex recent data projects are probably those that link survey data and machine-based data, device movement data and then new survey data. However, the most interesting project throughout the pandemic is 'Taking the Pulse of the Nation' - known as the "TTPN". The dynamic nature of the survey means the questions are constantly changing on a monthly basis to keep up-to-date with the changing focus of the survey, which leans heavily into the current socio-economic issues.
This project represented a learning curve for team members on how complex data projects can frequently present novel and unforeseen challenges, and require agile responses and an intimate connection with the data being collected, analysed and eventually passed through to key stakeholders. This impacts everyone involved in the project, constantly refining how the nuts and bolts of collecting data in complex segmentation arrangements can translate into an illuminating and richly informative output in the eventual hands of national stakeholders, including media companies.
In your opinion, what do you think is the most important message businesses need to know about how data can help their organisation?
We live in the data era - it is central to everything that businesses encounter in the modern hyper-connected and digital world. The world of data grows at an exponential rate that is simply impossible for any one person to fully comprehend - and especially the myriad ways that different sets of data interact and inter- react and shape the wonderful and exciting world that we live in. Roy Morgan works as a living organism to bring together complex data sets on all the significant industries in Australia.
With this wide and rich understanding of data, we have developed valuable segmentation tools to distil the maximum value for businesses looking to solve problems and find a competitive and comparative edge on their competitors. For instance, Roy Morgan's Helix Personas incorporates values, beliefs and attitudes, which are the best predictors of consumer behaviour. Businesses, brand owners and media agencies can then optimise marketing spend to effectively message those potential customers and, at the same time, find, and grow new markets. To truly grasp the marketplace in which a business operates, understanding the factors that drive consumer attitudes, behaviour, and spending decisions is vital - and data is central to that understanding.
Investing in data is an investment in the future of a business - it shapes its future.
Margin of Error
The margin of error to be allowed for in any estimate depends mainly on the number of interviews on which it is based. Margin of error gives indications of the likely range within which estimates would be 95% likely to fall, expressed as the number of percentage points above or below the actual estimate. Allowance for design effects (such as stratification and weighting) should be made as appropriate.
Sample Size | Percentage Estimate |
40% – 60% | 25% or 75% | 10% or 90% | 5% or 95% | |
1,000 | ±3.0 | ±2.7 | ±1.9 | ±1.3 |
5,000 | ±1.4 | ±1.2 | ±0.8 | ±0.6 |
7,500 | ±1.1 | ±1.0 | ±0.7 | ±0.5 |
10,000 | ±1.0 | ±0.9 | ±0.6 | ±0.4 |
20,000 | ±0.7 | ±0.6 | ±0.4 | ±0.3 |
50,000 | ±0.4 | ±0.4 | ±0.3 | ±0.2 |