Researchers have traditionally relied on univariate statistics (means, percentages) and bivariate statistics (correlations, cross tabs) for analysis. While essential, these approaches often fail to identify key insights or patterns in the data that are hidden to the “naked eye”.

• Factor Analysis – a useful tool to help determine which variables “go together” or behave similarly. This is often used to streamline a lengthy customer satisfaction survey. It can also be used to identify the key factors or dimensions that customers use in the evaluation of products.
• Cluster Analysis – similar to factor analysis except that it detects which individuals “go together” based on demographic, attitudinal or behavioral characteristics. This is typically used to segment markets.
• Regression Analysis – a multivariate technique used to predict an outcome (e.g., sales, share, defection, response, satisfaction) based on the information from other “independent” variables.
• “Drivers Analysis” – a term often used for analyses designed to explain the factors that impact customer satisfaction. The most appropriate “drivers analysis” procedure varies for a given data set but often entails a combination of a factor analysis and multiple regression.
• CHAID – a descriptive analysis technique that identifies the combination of characteristics related to a specific outcome. For example, this approach can be used to identify the set of characteristics related to dissatisfied customers, defectors, responders to a promotion, high value customers, etc. It can also be used to determine the combination of magazines or TV shows that maximize target reach.

Whether we work with your existing data or the data from one of our studies, we can help you get the most out of your customer information investment.