Environics Analytics produces our data in a way that allows users to evaluate behaviours or characteristics at the postal code or other geographic level. Each data point provided at the postal code level is a distinct variable that cannot be cross-tabbed with the other data.
For example, behavioural data allow us to identify the rate of CBC viewers in a postal code (and other levels of geography) but does not allow users to combine being a CBC viewer and a Honda owner. Instead, users would look at geographies (or segments) with high rates of both variables.
Why is this the case?
Modelled data often involve transformations, aggregations, or predictions that alter the original data structure. Cross-tabs rely on raw, unaltered data to accurately represent the relationships between variables.
The results from modelled data are often derived from underlying statistical models, which can introduce dependencies and correlations that are not straightforward to interpret through simple cross-tabulation.