In a time when almost anything can be measured, we must ask ourselves the most important question – Why are we measuring this data? Without a proper end goal in mind, the data we collect has the potential to become meaningless, overwhelming, or misleading.
Comparing data points can lead to the discovery of an unexpected correlation. This discovery can take creativity to determine. But the risk with this is correlation needs to be proved rather than inferred. Even if the data suggests a correlation, it does not imply causation.
For example, as ice cream sales increase, the rate of drowning also increases. Therefore, purchasing ice cream may cause drowning. Of course, this seems illogical as we can all easily recognize that both of these variables are affected by a third variable, the weather or season. Ice cream sales increase in the summer, when it is hotter outside and more people are likely to go swimming and risk drowning as it gets hotter outside as well.
This is the type of awareness that we need to be aware of when analyzing our own data as well as when reviewing the results of someone else’s data analysis. It is our responsibility to analyze the data as accurately as possible.
In the same way, presentation of data can greatly impact the interpretation. I started out talking about how data must be gathered with an end goal in mind. For some organizations, the end goal may be to cause some action by stakeholders. For example, The Girl Effect is representing data to bring awareness to the struggles that many girls face around the world as well as inspiring action by the viewer. In order to create an impactful story, the data must be represented in a certain way and leave out any data that may takeaway from the emotional effect on viewers. This is not unethical, but as a viewer, we must be diligent and aware of what data we are consuming as all of it is inaccurate to a point.