Our platform can display averages for numeric data points like age, time spent on media and household income.

Because most of our numeric data points are ranges (e.g. 2-3 hours), we first have to assign them with a midpoint value (e.g. 2.5 hours). We then multiply the midpoint value of each numeric data point by its corresponding universe (i.e. the number of real-world people represented by that data point). Finally, we sum up the values for each brackets and divide the result by the total universe for that question.

You can view the midpoints for each option in a crosstab, by crossing each data point with the average option, as in the screenshot below.

Looking at averages is a good way to quickly spot trends and differences across audiences, but these don’t capture as much detail as the individual options.

For the full picture, we'd always recommend looking at the distribution of individual options. For example, did your audience’s average time spent on podcasts increase because more people started listening, or because existing listeners are spending more time? Is the average income higher than expected due to a small number of high-income outliers, or is everyone in the audience more affluent than you thought? These are the kinds of insights you can uncover by looking at the individual data points to get a more nuanced understanding of your audience and what’s driving the story.