Multi-level projects present data in two or more levels and the unit of count varies across the different levels. The structure of a multi-level project allows for analysis of the relationships between a respondent, and, for example, their consumption occasions, of which there may be many. The data is organized hierarchically, with parent records (respondents) linked to multiple child records (events).
In this article
1. Explaining Multi-Level Data
When a survey includes questions about people as well as questions about events those people have been involved in, the data from that survey can be presented in two levels. One level represents the respondents (people), and the other level represents the events (such as consumption occasions).
When data is presented this way, it is possible to look at all the relationships between the characteristics of the people (such as age, sex, or income) and the characteristics of their events (such as when a drink was consumed, what brand was it, or where was it consumed).
The data are stored as records which are connected to one another through links Links are unique identifiers Learn more..
In this hierarchical database model, each child record has only one parent record, whereas each parent record can have multiple child records. A multi-level database may therefore have many more child records than parent records because each person at the parent level can, for example, have had many drinks, which are held the child level.
2. How are counts different?
The unit of count is what each record in the data represents. The unit of count may represent a respondent (person), or an occasion, a visit, or any other type of data. Data may be collected at multiple levels, for example, one of the files contains information about respondents and a separate file contains information about their consumption occasions.
Respondent/Parent Level Data
At the people level, each record represents a respondent.
In the example below, we can see that 30% of people said Cool Nut is their favorite brand.
Occasion/Child Level Data
At the occasions level, each record represents a consumption occasion. Each respondent is asked about their consumption for each brand they consume, so now we can calculate results based on people, occasions, and because the amount consumed is recorded, we can also calculate volume.
- 66% of people have consumed Cool Nut.
- Cool Nut was consumed in 43% of the consumption occasions.
- Across all occasions, 55% of the total volume consumed can be associated to Cool Nut.
Different types of data can be collected within a survey and you may have several data sets at the child level that each link to the parent level. You may also have another child level that appends to child level, sometimes referred to as a grandchild.
Where to from here?
Learn more about multi-level data