As a front runner in the field of choice modeling and training & development partner of Sawtooth Software, global leader in conjoint software, we are proud to host 3 online workshops and 2 presentations on the latest conjoint innovations and techniques at the virtual 2020 Sawtooth Software European Conference in Stockholm, Sweden:


Running a Conjoint Project from Start to Finish – Introductory

Tuesday 22 Sep | 09:00 – 13:00
Jeroen Hardon, VP Methodology & Transformation
Egle Meskauskaite, Senior Analyst

While theory of conjoint analysis is very important and much discussed at the Sawtooth Conference, with this workshop we want to take the practical approach and run you through the entire CBC study from start to finish.

We will go over each of the steps including data re-coding, counts, Logit, Latent Class and HB. In each of these steps we will also give you some tips and tricks on how you can get the most out of your data. How to model the data, interpret the results and what are the key things to look out for? We will discuss these and more based on a real data set and using Lighthouse Software.

Experimental Conjoint Solutions – Advanced

Tuesday 22 Sep | 14:00 – 18:00
Jeroen Hardon, VP Methodology & Transformation
Egle Meskauskaite, Senior Analyst

Sometimes standards are not enough to answer the research questions at hand and one has to deviate from the roads most travelled. We would like to get you on board for this 4-hour tutorial on advanced applications. Here we will focus on several challenging but very interesting extensions of choice modeling, including:

  • Custom statistical design techniques (designs using Lighthouse Studio and Excel; e.g. alternative-specific, frequency imbalance, pricing rules) and implications of these customizations
  • Showing different coding methods for faster processing
  • Combining multiple MaxDiff studies in one Latent Class estimation
  • Combining MaxDiff and CBC: different ways of data augmentation
  • Duct-tape solutions for the red-bus-blue-bus problem

A Practitioner’s View – Intermediate

Wednesday 23 Sep | 09:00 – 18:00 (divided into 2 sessions)
Jeroen Hardon, VP Methodology & Transformation
Egle Meskauskaite, Senior Analyst

Are you already (somewhat) experienced with conjoint analysis, but still struggle with questions like: “How many SKUs can I include in my study? Which method is the most appropriate for the business question? Which kind of none should I use? First choice or share of preference? What is the difference between preference share, market share and volume share? How many concepts do I show? Should I line-price my products? …” We do too!

Having done thousands of conjoint studies at SKIM, we have developed a good feeling for how to deal with these kinds of challenges. Therefore, we would like to invite you to join this session to discuss these topics, learn from us, but certainly also from the other participants’ experiences. Please prepare yourself for a lively and interactive session! After the session, you will have a better appreciation of the pros and cons of different methodologies, set-up specifications, simulation possibilities and…you will have learned why we most often reply to conjoint related questions with… “it depends”…

P.S. In case you have specific questions / topics you want to include or you want to use your own study as an example during this training, don’t be shy to contact us prior to the session (at least two weeks in advance please):



Assessing and Improving Individual-Level External Validity of Conjoint

Thursday 24 Sep | 11:50 – 12:25
Lois van der Molen, Senior Analyst
Menno de Jong, Analyst

How well can conjoint analysis predict real-life choices at an individual level? While conjoint methods and models have often been validated internally (by using holdout tasks and/or respondents), the number of comparisons of predicted with real-life choices is limited. Especially on an individual-respondent level.

A two-wave study is conducted to gain more insight in the external validity of conjoint exercises and simulations. In addition, factors outside of the conjoint exercise that influence consumers’ choices are identified (e.g. promotions or advice from others). Lastly, a comparison on individual level external validity is made between a traditional CBC and a filter CBC. The latter allows respondents to create their own consideration set using filters and sorting options, better mimicking online shopping behavior.

A New Way of Modeling Diminishing Returns for Binary Attributes in Conjoint Studies

Friday 25 Sep | 14:50 – 15:30
Gonzalo Javier Casais, Analyst
Joost van Ruitenburg, Director
Kevin Lattery, VP Methodology and Innovation

Being able to optimize the combination of attributes while avoiding steep diminishing returns is key both to researchers and clients. Unfortunately, standard HB models are not always up to the challenge. Built on the premise that the consumers confer value to the individual and independent attributes of a certain concept, standard HB models tend to overestimate the benefits of including numerous binary attributes. The aim of this study is to analyze how to best overcome the law of diminishing returns considering claims and binary (on/off) services in choice-based-conjoint studies by comparing 3 different modelling methods: a Machine Learning Empirical Bayes (MLEB) take on Lattery’s (2013) model, Benefits-Based model (Kim, D. S et al. 2017), and a shortcut parameter.