Elizabeth Horn is an expert in advanced analytics, such as choice and MaxDiff modeling, regression and predictive modeling, GIS analysis, and market segmentation. Below is a collection of blogs she has written.
You’ve cleaned the data of cheaters, bots, and other ne’er-do-wells. The data set is ready. But hold the analysis! You need to examine the data for outliers. These are extreme data points found in continuous, numerical entries, such as taxable income, age, and so on. Outliers can play havoc with the data.
During the course of most segmentation engagements, a typing tool is developed. This tool classifies future respondents into a segment using fewer questions than used in the original segmentation analysis. Vigorous application of the typing tool is necessary to achieve activation. The more companies integrate the typing tool into discovery and sales processes, the more likely they are to realize the full potential of their segmentation investment.
During tough economic times, companies may often seem insensitive to their customers, causing a loss in trust and loyalty. Price increases paired with decreasing value cut deep. There can be a more artful approach to pricing that can soften the blow for consumers while still managing profitability. Of course, pricing evaluation can be complex, so where should your company start?
Segmentation initiatives are expensive and exhausting. Done properly, by including stakeholder interviews, qualitative exploration, quantitative segmentation, qualitative persona development, and an activation workshop, segmentations can take months and require the ongoing attention of internal business partners. When the research and the initial activation process is finished, there remains the big job of socializing the segments throughout the organization.
Both “reliable” and “valid,” are used to mean “robust” or “accurate” in everyday speech. The concepts of reliability and validity are not interchangeable from a scientific perspective. These two words are not identical, and understanding the difference is important when interpreting research outcomes.
Segmentation is a very powerful tool. Leverage that power by applying the segmentation to your company’s customer database(s). Organizations that successfully classify their customers into segments increase the likelihood that their brand communications and new products will meet the needs of those customers.
Commentary on choice modeling is confined mostly to discussions of optimizing an entire product or service, its pricing, and perhaps even its inclusion in the broader portfolio. So what do we do with those products that are not wholes, but rather some individual component or ingredient? Often manufacturers want to optimize the features and the pricing for their product parts.
Companies that expect to survive must introduce new or improved products regularly. The reasons for this are numerous. With these pressures from purchasers, competition, and distribution channels, companies are faced with the task of rapidly introducing new products, sometimes at the expense of current ones.
An optimal suite of great products offered at acceptable prices is an integral part of a company’s strategy. But what sounds like a pretty simple proposition is not that easy in practice. Pricing strategies should encourage product purchase, promote customer goodwill, and, ultimately, maximize profit. Evaluating potential pricing strategies with historical or future-looking methods is critical.
Statistical significance testing is fraught with danger. “Getting it wrong” can translate into suboptimal business decisions at best and financial loss at worst. Although there are several potential pitfalls associated with statistical significance testing, these are the two main mistakes: Mistake #1 is a false positive and Mistake #2 is a false negative.
Non-response bias occurs when people who participate in a research study are inherently different from people who do not participate. This bias can negatively impact the representativeness of the research sample and lead to skewed outcomes. There are, however, strategies that may mitigate the impact of non-response bias that do not require large budgets and longer time periods.
Using well-established methodologies, qual uncovers emotions and motivations associated with human decision-making behaviors. Qualitative insights frame and then explain quantitative insights. It is impossible to measure something without first defining and understanding it. In the spirit of fostering insights based on a solid foundation, I offer this friendly advice to my fellow, quant-focused researchers.
I wonder how many beneficial scientific insights have been discounted or flat out ignored because of adherence to 95%? And in the market research industry, what great nuggets of truth have we inadvertently missed? To its credit, market research is less rigid in its significance testing. Some companies even maintain a standard of 90%, recognizing that 95% may cause them to overlook something important.
A comparison of 3 different pricing research methods: Choice Modeling vs. Van Westendorp vs. Gabor-Granger. Choice modeling techniques--the “good” pricing methods--should be recommended first to assess product pricing. When clients are budget-strapped and time-pressed though, “good enough” methods, such as the Gabor-Granger analysis, can provide sufficient guidance.
