Statistics and data are often very difficult topics to grasp, even for those directly involved in the field. However, Spiegelhalter did a fantastic job in not only explaining some of statistics’ core concepts, but also applying them to real-life scenarios as well as successfully making a case in advancing data literacy everywhere.

COVID-19, climatic trends, economic indices, and metrics that quantify racial inequalities are but few of the many examples that demonstrate data’s important role in everyday life. However, despite data’s seemingly objective nature, how it’s processed, communicated, and understood are prone to errors or intentionally mischievous actions. Any flaw in what the author described as the PPDAC framework (Problem, Plan, Data, Analysis and Conclusion) could have disastrous consequences. An example of why data literacy and proper communication of data findings in full is the ongoing but misleading narratives that COVID-19 vaccines are “ineffective” because allegedly the risk of getting infected, getting hospitalized from COVID-19, and/or dying from it is negligible between non-vaccinated groups and groups with varying levels of dosage. The reality is that the people who are pushing those narratives fail to account for those numbers on a group-by-group basis, and only look at the raw numbers. For example, if we run a hypothetical test (I say hypothetical because the ethics of this imaginary test would not bode well in the real world) where 10 unvaccinated people and 100 quadruple-dosed vaccinated people were infected with COVID-19, and 1 unvaccinated person died and 4 vaccinated people died, you can see how, proportionally, the mortality was lower for vaccinated people even though it was numerically higher. This is a common flaw (not just limited to vaccination) where people would Interchangeably use “absolute” and “relative risk”. Another common flaw outlined by the author is ignoring confounding factors that could play a role in two variables’ correlation (for example, is the positive correlation between higher educational attainment and brain tumor prevalence reflective of educational attainment, or more reflective of better socioeconomic status that allows people with a higher status enough financial fluidity to access education as well as healthcare procedures that does a better job of detecting brain tumors?)

Whether it comes to marketing firms building up hype for their product, politicians pointing to certain economic indices, pharmaceutical companies lauding the efficacy of their products, universities boasting about their rankings, and so forth, many players will use (and, unfortunately more often than not, misuse) data to push their agendas. With the advent of big data, it becomes even more crucial for data literacy to be augmented accordingly.