Our analysts are conversant with the latest multi-variate techniques and can conduct analysis across any specified measures using cluster, factor, correlation and regression analysis. By drawing on these techniques we can conduct segmentation studies for clients to break down populations into segments defined by particular characteristics in order to finely target marketing or communications campaigns.

Segmentation studies begin with comprehensive qualitative research from which typically a number of key attitudinal statements are developed. These statements will reflect attitudes on a particular issue or about an organisation which are then measured in a stand-alone quantitative survey.

A number of multi-variate statistical techniques are then used to identify key attitudinal groups or segments of the population, which can then be examined in terms of their demographics, behaviour, attitudes and size.

Cluster analysis is one technique which attempts to identify relatively homogenous groups of cases based on selected characteristics, using an algorithm that can handle large numbers of cases. The aim is to identify groups which are as different as possible from each other, while cases within a group are as similar as possible to each other.

UMR utilizes a number of multi-variate techniques including:

• K-Means cluster analysis
• Factor analysis
• Answertree analysis
• Regression analysis
• Correlation analysis.

The final multi-variate methodology used is determined by the nature of the data collected and the technique that provides the most robust and meaningful outcomes.

Back