The scope of our tools and methodologies
Some old favourites, a twist on a theme and some new ones too. Flexible, highly robust methods for every occasion.
Successful segmentations are the result of strong planning, good communication and the use of best-in-class statistical models. We place people into groups based on their data and use their group membership to make predictions on how they are likely, on average, to respond to a set of underlying questions..
Key Drivers Analysis addresses the questions: “Which combination of possible explanatory variables best explains the data I see for some question of interest?” and “what is the unique contribution of each predictor?” This question, we are trying to explain, can sometimes be an interval (e.g. 0-10) scale such..
Decision Tree Analysis is an exploratory method which explains some variable of interest without using a strict regression model. It falls half-way between the categories of Segmentation and Key Drivers Analysis. It is designed primarily for situations where: The variable of interest is a two category (Yes / No)..
Choice modelling is used to estimate the probability that an individual will choose a particular option from a set of alternative options. This type of modelling is sometimes referred to as Conjoint Analysis or Choice-Based Conjoint (CBC). Predicted probabilities can be averaged over a sample, to determine the..
Principle Components Analysis summarises dimensions of variables within data. Data reduction techniques, such as Principle Components Analysis or Latent Class Factor Analysis, are extremely useful summarising the underlying dimensions among MANY variables. They enable us to derive a FEW composite variables which explain the correlations and patterns of..
Brand Mapping is a technique which gives a 2D pictorial approximation of the associations between rows and columns in a frequency table. It is so called because in a classic application the columns of the table represent brands and the rows represent attributes. The most common type of..
Structured Equation Models are systems of predictive linear models. They involve complex relationships between predictors and dependent variables and often dependent variables and other dependent variables. They can be used to test whether data supports a particular hypothesis about a system of relationships between variables, where there are..