CHAID

MRSI utilizes CHAID (Chi-square Automatic Interaction Detector) to analyze the relationships between a dependent measure and a large series of independent variables that may themselves interact.

CHAID creates a decision tree model which shows which independent variables more strongly "predict" or are associated with the dependent variable.

Cluster Analysis

MRSI uses Cluster Analysis to classify respondents into market segments, that is, subsets of consumers who are similar to each other, but different from consumers in other segments. People within a given market segment are likely to respond similarly to a distinct marketing strategy. MRSI typically examines respondents' data patterns on a series of attribute ratings, such as importance, benefit, attitudinal, or psychographic ratings to cluster respondents.

Click here for more information on how MRSI can help with your segmentation needs.

Concept Highlighter^SM

MRSI uses Concept Highlighter^SM to make it easier than ever to understand the specific words, phrases or visuals that are liked or disliked by consumers. You can also measure purchase intent, believability, and more, all in a visual experience that is natural and engaging for both respondents and for you.

Your body and mind take a pounding leaving you tired - without energy physically and mentally. NRG Booster Original energy drink gives you the edge you need to keep on keepin' on - at your highest level! Our unique energy boosting formula will take you to where you want to be - WITH ENERGY! Pound one! Available in: 10 oz. bottle for $2.39 25% say Nothing makes them want to purchase

Click here for more information on MRSI's Concept Highlighter.

Conjoint Analysis/Discrete Choice

MRSI uses Conjoint Analysis/Discrete Choice to uncover the product features that have the greatest impact on complex consumer decisions such as purchase intent or product preference. In conjoint, respondents make trade-offs on product features, allowing conjoint analysis to uncover purchase motivations respondents may be unable to articulate or not realize. The analysis provides an estimate of purchase interest for all combinations of product attributes.

Conjoint Analysis can be ratings-based, choice-based, and a hybrid of both.

Correlation Analysis

MRSI uses Correlation Analysis to help understand what specific features of a concept or product may be driving consumer's interest to purchase or overall liking of the product or idea. Correlation Analysis is a statistical procedure that can help to explore the extent to which two variables are related.

Customer Value Analysis (CVA)

MRSI uses CVA to measure customers' assessment of the value proposition for key brands in a category. This technique can also help identify key customer value attributes to support premium pricing, track the value proposition over time, identify and prioritize key improvement opportunities, increase brand value relative to competitors while maintaining a brands' price structure, identify upside and downside pricing opportunities and develop sales plans to address key trade value opportunities.

Discriminant Analysis

MRSI uses Discriminant Analysis to classify respondents into mutually exclusive groups, based on ratings to a set of predictor variables, such as importance ratings, psychographics, etc. The technique results in a regression-type equation to predict group membership.

A common use of Discriminant Analysis is to predict target market membership, but it can also be an effective tool for gaining insight into groups such as heavy vs. light users, loyal vs. non-loyal customers, etc.

Factor Analysis

MRSI uses Factor Analysis, a data reduction technique, to examine the interrelationships among a larger set of variables and to explain these variables in terms of their underlying dimensions, or "factors." Factor Analysis is typically run to reduce the data from an unmanageable number of attributes (say 50) to a more manageable number of factors (say 7-10).

Gabor Granger

MRSI uses the Gabor Granger pricing technique to create a situation where customers are exposed to real price changes with real demand pressures in order to obtain price elasticity data. The technique is typically used to measure changes in market share/volume sales at different prices and understand brand interaction with competitors.

Hierarchical Bayes

MRSI uses Hierarchical Bayes to evaluate choice data, estimate utility values for conjoint analysis, and calculate coefficients in regression analysis.

Hierarchical Bayes is a powerful tool with a number of critical advantages over traditional methods of estimation. The primary advantage is the ability to calculate respondent-level utilities which results in better predictions.

Latent Class Analysis

Latent Class Analysis (LCA) is a statistical tool used to relate observed variables to a set of unobserved (latent) variables. Applications of LCA include segmentation, regression analysis, evaluation of choice data, and data reduction.

Although Latent Class Analysis can be a useful tool, other more practical techniques with additional benefits have emerged which tend to limit the need for this technique. MRSI typically uses Hierarchical Bayes (HB) instead of LCA when evaluating choice data and Convergent Cluster Analysis (CCA) rather than LCA for segmentation.

Maximum Difference Scaling (MaxDiff)

MRSI uses MaxDiff as an approach for obtaining preference or importance scores for multiple items (brand preferences, brand images, product features, advertising claims, benefit statements, etc.). The scores generated from this exercise demonstrate greater discrimination among both attributes and respondents.

Click here for more information on how MaxDiff can help with your research needs.

Penalty Analysis

MRSI uses Penalty Analysis to provide product developers with diagnostic information to guide product improvement decisions prior to a launch of a new product, new flavor, or formulation change. The goal of Penalty Analysis is to prioritize product improvement decisions based on the impact that product characteristics which are not "Just Right" have on consumers' overall satisfaction with the product.

Perceptual Mapping

MRSI uses Correspondence Analysis and MultiDimensional Analysis of PREFerence (MDPREF) to create Perceptual Maps. Perceptual Mapping is a graphical technique used to summarize the relationships between brands and their ratings on attributes. The closer two brands appear to each other, the more similar their images. Likewise, the closer a brand appears to an attribute, the more it is associated with that attribute.

Regression Analysis

One method MRSI uses to evaluate attribute importance is regression analysis. In regression analysis, numerous product attributes are used in an attempt to predict a dependent variable such as purchase interest or overall rating. The output of regression - standardized regression coefficients - provides an idea of the relative contribution each attribute makes in predicting a dependent variable.

TURF Analysis (or Coverage Analysis)

MRSI uses TURF analysis to help determine the combination of products in a line that can achieve the highest level of consumer interest (or market "coverage"). This technique is commonly used for extending established product lines, but can also be used for a new product line.

Van Westendorp

MRSI uses Van Westendorp to help guide the pricing of new products early in the product development process. This technique relates price changes to the perceived quality of the product and it determines the range of acceptable prices for a new product and estimates an "optimum" consumer price point.