25 January 2013 | Blog
We’ll be hosting a workshop on probability models for media analysis at our office next month. We hope you can join us!
Probability Models for Media Analysis
Peter S. Fader, Frances and Pei-Yuan Chia Professor of Marketing, the Wharton School of the University of Pennsylvania; Co-Director, Wharton Customer Analytics Initiative
Bruce G.S. Hardie, Professor of Marketing, London Business School
Thursday, February 14, 2013
9:30am – 5:00pm
460 W 34th St, New York, NY
Central to a complete understanding of today’s leading-edge media research techniques is a sound intuitive appreciation of the basic behavioral and methodological foundations upon which these sophisticated tools are built. For example, emerging “hot topics” such as hierarchical Bayes models and hidden Markov processes are often built on simple probability modeling concepts (e.g., Poisson counts, Bernoulli “coin flips,” and exponential interpurchase times) — yet how many researchers are comfortable at precisely defining these concepts or explaining the motivation for using them?
This workshop aims to fill in these gaps by bringing practitioners fully up to speed on the basic methods that may underlie many of their current or future research activities. Our two broad objectives are (1) to review the essential terminology and logic associated with the area of probability models as applied to media research problems, and (2) to develop participants’ skills through a set of data-oriented case studies that demonstrate the model building process in detail. We will illustrate all of the steps required to develop a probability model, estimate its parameters, interpret the results, and draw appropriate managerial conclusions from it. Careful and extensive use is made of the Solver tool in Microsoft Excel, which makes it possible to construct all of these models within a familiar spreadsheet environment. By the end of the tutorial, participants should be quite comfortable with all of the aforementioned principles and models and the managerial issues that surround them.
This program will benefit all media analytics professionals – as well as more senior managers who want to gain a firmer grip on these concepts and methods. The material is somewhat technical, so some basic aptitude with probability/statistics would be beneficial for participants. For instance, it helps (but is by no means required) to have a little familiarity with basic probability distributions (such as the Poisson and the binomial), even if the details are largely forgotten. Similarly, participants should be comfortable with Microsoft Excel, although there is no need for any advanced capabilities (we will rely exclusively on ordinary “built-in” Excel functions). Finally, participants may wish to bring a laptop to follow along with the model-building exercises, but it is not required. All we ask from each participant is to bring an open mind, a sharp pencil and a high level of interest in media research. All materials presented (including the detailed spreadsheets) will be made available to all participants immediately after the seminar.
Lunch will be provided