expect great answers

vienna

Kirsten

Kirsten Pijpers
Marketing & Sales Coordinator
Research Services & Software
Based in the Rotterdam office
+31 10 282 3500

SKIM/Sawtooth Event 2011 - Training descriptions

Do you want to know more about our trainings? This page provides you with a short description for each session. Click on a title and find out.


Menu-Based Choice beta tester training

Bryan Orme, Sawtooth Software

MBC is yet another flavor of conjoint analysis. It involves showing respondents multiple items on a menu, and asking respondents to pick from one to many. Common examples include restaurant menus, configurators for technology products and durable goods, and mixed bundling/a la carte product selections.

During this two-day workshop, attendees will gain practical experience using Sawtooth Software’s new MBC software (beta version). Only analysts with significant experience in CBC and understanding of econometric modeling principles (coding design matrices, running estimation routines) should participate. MBC software requires more expertise on the part of the user than other conjoint tools from Sawtooth Software. Those attending the training become beta testers, and may use the beta software for project work until it is released v1 (probably Q1, 2012). The fee for attending this workshop may be applied toward the future purchase of MBC v1 software.

 

Introduction to market simulations

Brian McEwan, Sawtooth Software

The greatest value from conjoint/choice analysis is found in the what-if market simulator. The market simulator gives business decision-makers an intuitive and practical tool for testing specific product scenarios involving specific competitors. The results are expressed in terms of “shares of preference,” which are percentages summing to 100.

If you are focusing only on conjoint part-worths and importances, you are missing an important context that directly affects proper decision-making. We will introduce the main models for simulating product choice: First Choice, Share of Preference, and Randomized First Choice. We’ll also demonstrate how to use simulators to position products, assess line extensions, derive demand curves, and to optimize product offerings with respect to goals such as share, revenue, or profit, and look at various ways to report conjoint analysis results.

 

Introduction to statistics for marketing research

Keith Chrzan, Maritz Research

This tutorial provides a very basic, non-mathematical introduction to statistics. Participants will learn the basics of statistical testing, including:

  • How to know when to use which statistical test
  • How to use an intuitive statistical testing tool, a free download from the internet
  • Participants will not be using formulas and calculators will not be necessary – the focus is on a practical, conceptual understanding rather than on computational busy-work

Hands-on exercises will provide the class with data to test using the software, and these “case studies” will reinforce what participants learn from the presentation.

The presentation concludes with a brief conceptual introduction to selected advanced statistical techniques:

  • Predictive modeling (regression, logit)
  • Segmentation (cluster analysis, tree-based modeling)

This introduction may make the presentations on the last day of the conference more accessible to participants.

 

Introduction to Choice-Based Conjoint

Richard Neggers, SKIM

This tutorial reaches out to researchers who are either new to Choice-Based Conjoint analysis or ones that have been applying the basics and seek to gain more insights into this methodology.

Richard briefly discusses Discrete Choice Modeling, as stepping stone to Choice-Based Conjoint. He then explains the motivation and theory of this powerful trade-off technique by means of intuitive practical examples.

 

Advanced CBC designs

 Jeroen Hardon, SKIM

A 4-hour workshop that focuses on a number of challenging and interesting extensions and applications of choice modeling, including: alternative-specific designs, bundling, optional choice models, and pricing models with special constraints (such that premium products are always higher priced than non-premium products). In this advanced session, Jeroen intends to show you some of the more interesting and useful possibilities within the family of discrete choice methods. The techniques described usually involve custom work that goes beyond the options provided in standard Sawtooth Software.

 

Pricing from company, consumer and research perspective - an overview

 Maureen Arink, SKIM

This 4-hour workshop looks at pricing from 3 different angles: the manufacturer, the consumer and the researcher. You will see how companies may deal with pricing and what challenges they face; how consumers may perceive and react to prices, and which tools we as researchers can use to bring both together. Two pricing research tools in particular will be looked at: Choice-Based Conjoint and Van Westendorp Price Meter. You will see the differences between the tools, their (dis)advantages, and when and how to use them.

 

Introduction to Menu-Based Choice

 Bryan Orme, Sawtooth Software

(Part 1) MBC is yet another flavor of conjoint analysis. It involves showing respondents multiple items on a menu, and asking respondents to pick from one to many. Common examples include restaurant menus, configurators for technology products and durable goods, and mixed bundling/a la carte product selections. Bryan will describe how to design and analyze these kinds of studies from a practical standpoint using the following commonly used tools: randomized designs, counting analysis, and logit/HB.

(Part 2) Sawtooth Software has recently entered the beta phase of its new software system for MBC (Menu-Based Choice) analysis and simulations. Bryan will briefly show attendees what the software can do. We won’t have time in this session for attendees to actually work with the software, so this will be a “show and tell” session. (Those interested in becoming a beta tester and getting practical experience on the software should attend the beta training sessions on Oct 25-26.)

 

Product / portfolio optimization

 Maureen Arink, SKIM

A 2-hour workshop in which we will have a look at how to use Choice-based Conjoint for Product and Portfolio optimization exercises. Identify what it is that you need to optimize on: ask yourself “what does 'optimal' mean to me?” We will discuss considerations and limitations of optimizing using CBC, and how optimization exercises can be approached. During the workshop you will be asked to do an optimization exercise yourself as well.

 

Introduction to customer satisfaction research

 Keith Chrzan, Maritz Research

Customer Satisfaction Research is one of the three major categories of custom research (the others being Brand Research and New Product Development Research). This tutorial offers and introduces Customer Satisfaction Research, including:

  • What is customer satisfaction research?
  • How are customer satisfaction studies designed and analyzed?
  • How end users benefit from customer satisfaction studies?
  • How does customer satisfaction research relate to loyalty?

In many ways customer satisfaction data is the least well-behaved kind of data we as researchers will ever face; part of the presentation covers ways to address common data problems.

The presentation concludes with a discussion of how some firms use their customer satisfaction data as part of an integrated customer feedback system, combining customer survey data with social media and other forms of customer feedback data, and linking customer satisfaction survey data with upstream and downstream business metrics.

 

Working with SSI Web

 Jeroen Hardon, SKIM

(Part 1) In the first part of this course we will show you the basics of SSI Web. The powerful list-building feature is one of many topics we will discuss. Class members may bring a laptop PC with Windows XP (or later) installed, but it is not required. A temporary student lab version of all software needed for this workshop (for non-commercial, training use only) will be given to attendees that wish to follow along with the examples.

(Part 2) Even though SSI Web is easy to begin using, there is an amazing degree of flexibility and power awaiting the adventurous and more experienced user. This second part of the course assumes you are already acquainted with the software through prior use or having followed the first part.

Specifically, the course will demonstrate a number of power tricks that will open your eyes to new possibilities to accomplish challenging tasks and impress your clients. You’ll see how you can take on new work and problems you previously thought could not very easily be done. Many of these tricks involve Perl and JavaScript. We'll demonstrate the features individually and then show unique ways in which tools can be combined to take full advantage of SSI Web's simple but powerful interface. Class members may bring their laptops.

 

MaxDiff for item scaling and TURF

 Brian McEwan, Sawtooth Software

Researchers are commonly asked to scale/prioritize lists of items, attributes, brands, statements, etc. Maximum Difference Scaling (MaxDiff) has emerged as a leading research tool that is generally superior to standard rating scales. MaxDiff scaling has many similarities to conjoint analysis, but it is easier to understand and use, and more generally applicable to a wider variety of problems.

A recent (2011) survey of Sawtooth Software clients showed that 52% of their firms had used MaxDiff during the previous year (up from 8% in 2005). This tutorial demonstrates how easy it is to apply this technique using the SSI Web system. TURF stands for Total Unduplicated Reach and Frequency, and is a simulation approach for finding groups of items that “reach” (satisfy) the most people. Some researchers are using TURF together with MaxDiff for portfolio optimization. Attendees will come away with a clear understanding of when to use MaxDiff and how to do it.

 

Experimental Conjoint

 Richard Neggers, SKIM

Purpose of this workshop is not to lecture but to discuss. Richard will demonstrate deviate approaches of conjoint modeling. The experimental nature of the workshop becomes clear as he guides you through original design or analysis practice for more complex conjoint research implementations.

 

CBC/HB modeling: Beyond the basics

 Bryan Orme, Sawtooth Software

Just about anybody can perform Hierarchical Bayes (HB) estimation by using the defaults in the CBC/HB software and clicking a few buttons. In this session, we’ll probe other settings and options in the software: constraints, linear estimation of quantitative functions, user-defined coding, prior variance, covariates, on-screen diagnostics, and convergence. We’ll discuss how to make decisions regarding inclusion of interactions in CBC models, overfitting concerns, as well as scale factor issues. We’ll also show how data from experiments other than standard CBC or MaxDiff may be analyzed, and how to avoid some pitfalls. We’ll mainly stay to a conceptual level, rather than delving heavily in math detail.

 

Cluster Ensemble Analysis using CCEA

 Brian McEwan and Rich Johnson, Sawtooth Software

Cluster analysis has been a long-time standby in the market research community for segmenting respondents into groups, where the differences within groups are (essentially) minimized and the differences between groups are maximized. However, recent advances in the machine learning literature have shown that leveraging cluster ensembles can improve upon standard cluster analysis results. The presenters will demonstrate how to use Sawtooth Software’s CCEA system to perform standard K-Means cluster analysis, and then will show how the software employs cluster ensembles to improve the solutions. This presentation will largely be conceptual, and you will gain a greater understanding of how cluster analysis works, why it is useful in marketing research, and how advances in cluster ensemble procedures are improving respondent classification accuracy.

 

Presenting your results with great impact

 Gerard Loosschilder, SKIM

When developing impact-full presentations, do you ask yourself "so what" with every fact you're presenting? What's the implication of this fact for the client's business and for your audience? The "what if" will then come naturally. It'll turn you into an empathetic business consultant.

Want to know more? Don't hesitate to give us a call or drop an email!