When Professor Kamel Jedidi began teaching a course on pricing several years ago, he was frustrated by the standard methods of measuring a consumer’s reservation price — the point where the consumer is indifferent between buying and not buying a given product. Market researchers typically ask consumers directly how much they are willing to pay. But this approach yields biased results, since consumers tend to overstate their responses for prestigious brands and lowball their responses for most other products.
“So I asked myself, how can we do better?” Jedidi says. In the late 1980s Professor Rajeev Kohli had introduced a more accurate method that uses conjoint analysis — a psychometric concept widely used by marketers. In a series of recent studies, Jedidi improved on Kohli’s approach by combining it with economic utility theory and recent advances in statistical estimation techniques.
By presenting consumers with a series of choice sets and then building a model that describes their preferences, you can use this method to infer their reservation prices for various product configurations. The basic conjoint method assumes everybody is in the market, which leads to inflated demand estimates. Jedidi’s method is closer to reality because it allows people to opt out if their reservation price is below all the products offered. In a paper with John Zhang of Wharton, Jedidi demonstrated another advantage of the augmented conjoint method: it allows you to decompose your demand estimates into gains from market expansion, gains from switching and losses from cannibalization.
In another study, Jedidi, Sharan Jagpal of Rutgers and Puneet Manchanda of the University of Chicago adapted the new method to product bundling scenarios. If you want to offer a bundle of products, you can use this approach to build a model that helps you pick the bundle/price combination that maximizes your profits.
More recently, Jedidi, Kohli and Raghuram Iyengar of Wharton developed a conjoint method that measures reservation prices for products with a tiered pricing structure.
In a set of experiments, they presented people with a series of wireless phone service plans. Variable attributes included the monthly access fee, the per-minute fee, the number of free minutes per month and features like Internet access and a rollover option.
“This method builds a model for how people make decisions when they have two-part tariffs,” says Kohli. “The model allows you to estimate the different parameters that go into measuring the reservation price for each part.”
For a particular product, you can use this method to compute the mean reservation price and the variance within a given population. And by varying the price and features, you can infer the reservation price for specific attributes. “If consumers react a lot to a price change as compared to a feature change, then clearly price is more important than the feature,” Jedidi says. “We’re basically trying to understand the tradeoffs that people make.”
You can also estimate the market share and level of unit sales for different product configurations. “Given a certain product or service, you could determine what percentage of people will buy it and how many they will buy,” Jedidi says. “This is the core information that managers need to decide on optimal prices or on a pricing structure.”
This method helps you segment your customers based on willingness to pay so that you can match your offerings to the interests of each segment. “The whole concept of pricing strategy lies in trying to understand how much value people attach to products and services,” says Jedidi. “If you can segment consumers into homogeneous groups of people who are willing to pay more for one thing or a bundle of things, then your pricing is nicely matched along those dimensions.”
Jedidi notes that most of a firm’s activities — creating products and services, making them conveniently available and educating consumers about them — center on value creation. “Pricing is the only variable where the firm has a chance to capture that value back from consumers,” he says. “So good pricing can lead to future success. Bad pricing can leave money on the table and is likely to jeopardize the firm’s long-run performance.”
Kamel Jedidi and Rajeev Kohli are professors of marketing at Columbia Business School.
Professor Jedidi has taught New Product Development, Marketing Research, Managing Marketing Programs, and Applied Multivariate Statistics. He has extensively published in leading marketing, statistics, and psychometric journals, the most recent of which have appeared in the Journal of Marketing Research, Marketing Science, Management Science, the International Journal of Research in Marketing, and Psychometrika. His substantive research interests include pricing, new product development, and market...
Rajeev Kohli is a professor in the Graduate School of Business at Columbia University. He has a doctoral degree in Applied Economics and Decision Sciences from the University of Pennsylvania; an MBA from Northern Illinois University; and a bachelor's degree in Electrical Engineering from BITS, Pilani, India. His research interests are in models of consumer preference and choice, techniques for new product development...
Read the Research
Kamel Jedidi, Sharan Jagpal, Puneet Manchanda
"Measuring Heterogenous Reservation Prices for Product Bundles"
Kamel Jedidi, Z. Zhang
"Augmenting Conjoint Analysis to Estimate Consumer Reservation Price"