In this article
- Choosing your descriptors
- Discover analysis
- Add descriptors or discover selections to your analysis
- Remove descriptors from your analysis
- Switching between standard and discover analysis
- Special bubble chart
1. First things first - choosing your descriptors
Descriptors are the variables you want to use for profiling. Descriptors can include demographic, psychographic, or behavioral variables, or some combination of all these.
Selecting your descriptors is an iterative process. The key is to try to avoid variables that will dominate your analysis.
To achieve this:
- Choose axes that do not have too many elements, For example, instead of using the Age axis, use Age (Grouped) axis.
- For rating scales, it is best to use summary axes. For example, instead of using Satisfaction Detail axes, use Overall Satisfaction – NZ (Grouped).
- Don’t double up. You can use the Age or Age (Grouped) axis but not both.
- Measures are currently not supported.
- With axes that have too many elements, the data may be spread too thin. You should use variables with elements that have a robust sample.
Flag a descriptor
To mark a variable as a descriptor, select the relevant axis and choose describe on/off under flags from the design menu.
As you move on with your selection, you can use the project tree filters to identify the variables that have been flagged as descriptors.
If you are a Creator (non-owner) or an Explorer, you can see the items flagged as descriptors by the project owner, but you can only flag as descriptors items that you own (i.e. constructions).
2. Discover analysis
There are a couple of ways for you to achieve this:
a) From an existing analysis
On a table view, select the group you are interested in profiling. Selecting will enable the Discover option located in the modify menu.
Discover will profile a target group against the set of descriptors you have defined. The Discover table ranks the rows so that the descriptors that most differentiate your target from others rise to the top, and those that are less likely differentiators go to the bottom of the table.
b) Drag and drop from the project tree into the analysis pane
From the project tree, select the group you are interested in profiling (i.e. Discover selection) and drag it into the Discover analysis zone.
As a default, discover will use the first element of the axis selected as the target (i.e. from the Top 10 Markets the element Australia). You can change the target by selecting the item you want to use and then choosing the option TARGET under tests in the modify menu.
Discover also sorts the groups across the table so those that are most similar to the TARGET are closest and the ones that are most different are furthest away. Rows are ranked so that the descriptors that most differentiate your target come to the top.
3. Add descriptors or discover selections to your analysis
After creating a Discover analysis, you can still interact with your descriptors and discover selections.
You can add or replace descriptors in your analysis with any axis from the project tree, even when not flagged as a descriptor. You can achieve this by dragging and dropping the relevant variables into the Discover Descriptor drop zone.
The same is true for your discover selections; you can add groups you are interested in profiling by dragging and dropping into the Discover Selection drop zone.
4. Remove descriptors from your analysis
You can unflag descriptors by selecting the relevant axis and choosing describe on/off under flags from the design menu.
You can also remove them from your discover analysis by using the interactive title and de-selecting the descriptors you don’t wish to use.
5. Switching between standard and discover analysis
After creating a discover analysis followed by a standard analysis you can switch between standard and discover analysis using the toggle under the visualise menu.
6. Special bubble chart
Under the visualise menu you can find the special bubble chart. This chart is a visual representation of what differentiates the profile target from the group.
This chart shows the size, proximity, and level of differentiation of each subgroup.