TRC

By Rajan Sambandam

Background and objectives

As part of its brand management strategy, a major energy utility (ABC Company) wanted to measure its brand image and identify specific image attributes that had the greatest impact on overall impressions of the company. In this way it could gauge its current performance in an increasingly competitive market, and prioritize image improvement efforts based on what was most important to consumers.

Notes on methodology

We were commissioned to design and conduct research to serve the above-stated objectives. Telephone research was conducted among 1,207 household decision-makers within the company’s service area. Each respondent was asked to rate the overall image and overall quality of ABC Company, and to evaluate the company on a series of imagerelated statements.

In total, interviews averaged approximately 15-minutes in length. Overall image and overall quality were measured using a five-point scale: excellent, very good, good, fair, or poor. Reactions to image-related statements were captured using a five-point agreement scale: strongly agree, somewhat agree, neither agree nor disagree, somewhat disagree, or strongly disagree.

Two models of brand image were produced: one using traditional multiple regression; one using Satiscan™, TRC's proprietary means of key driver analysis. The bulk of this case study focuses on a comparison of these two models. But first, we present for the reader a brief description of Satiscan™.

A brief description of Satiscan™

Satiscan™ is an analytic method developed by TRC specifically to address questions such as those posed by ABC Company. Using a directed search algorithm, Satiscan™ produces a map of brand image. This map can be used to identify those aspects of service that have a direct impact on image, those that have an indirect impact on image, and those that have no noteworthy impact on image.

This is a significant development in key driver analysis. Traditional methods (typically regression analyses) can only identify direct impacts on satisfaction, and ignore the fact that aspects of brand image inevitably interrelate to each other, and hence have indirect as well as direct effects on a customer’s overall perceptions of a company.

Satiscan™ reviews all possible path models in relation to customer responses and only then determines the ideal model of brand image. This may not seem like a tremendous difference until one realizes there are literally thousands of possible path models to choose from, and the odds of choosing the optimal one in advance are quite slim, unless there is a precise theory to guide model building.

Comparing a Satiscan™ model to a traditional regression model

The difference between Satiscan™ and traditional regression analysis is clearly shown by comparing two maps developed for ABC Company. Figure 1 is the view of brand image put forth by traditional regression.

To read the rest of this article and have access to the entire TRC white paper library, please click here.