The table above shows a crosstab of two Pick One questions. It shows that people aged 65 or more are more likely to have said they Like the brand (Pepsi Light) than the overall percentage (13%).
Although this intuitive understanding is essentially correct in terms of how to interpret the data, it is not, at a technical level because the 24 people in the 65 or more category are included in the total sample of 105. Thus, if we compare the 24 with the 105 we would be double-counting (or, to use the more formal statistical language, we would violate the assumption of independent samples).
The only way that people 65 or older can be different to the total is if they are different to the people that are not 65 or older. To test whether that is true or not, you need to collapse all the categories other than Like and 65 or more.
- Combine all categories other than 65 or more into a single category
- Combine all categories other than Like into a single category.
The test used to highlight the 43% on this table is precisely the same test as used in the table above (i.e., when creating the larger table. Q automatically created lots of these smaller tests in the background and uses these to compute significance. However, when using Multiple Comparison Corrections it is possible to get situations where the collapsed table will have a cell marked as significant and the non-collapsed table will not (and vice versa).