About this session
We both produce and read measurements and statistics every day, be they qualitative or quantitative. Often, we take this information at face value, but how reliable is the underlying data?
In this session, we take a look at survivorship bias, a data collection error (or is it an interpretation error?) where we only see a subset of a real representation, and its impact on how we analyse our security awareness campaigns and programmes.
One common example is that of publicly successful individuals. There are thousands of TikTok and Instagram famous influencers, for example, who make big bucks promoting products and services. With the visibility of these individuals, but lack of visibility of all those who tried and failed, how do we know the true success rate of an aspiring influencer?
Collection methods which are potentially biased to the data supplied or require criterion are flawed if not acknowledged, and can lead to false conclusions.
So, whether you’re looking at your chances of succeeding on TikTok or the performance of your security awareness campaigns, this session will help you learn how to recognise the holes in the data you collect and interpret.
Speakers
Have a question on this talk?
Send it to the presenter. The team passes it on and the reply comes to you by email.
