BayesiaLab Seminar in Cincinnati: Key Drivers Analysis and Optimization with Probabilistic Structural Equation Models
The Seminar at a Glance
In this half-day seminar, we present a complete workflow for developing a Probabilistic Structural Equation Model (PSEM) based on Bayesian networks and utilizing the BayesiaLab software platform. Our objective is to identify key drivers of satisfaction with a PSEM that is machine-learned from consumer survey data. A key challenge in this context is to resolve the conflict between "driver" as a causal concept versus the non-causal nature of non-experimental survey data. Furthermore, we illustrate how quantifying the joint probability of hypothetical scenarios is critical for establishing priorities for improving customer satisfaction.
Participants who complete this seminar program will automatically receive a BayesiaLab certificate after the event. All BayesiaLab badges and digital credits are managed via Credly, which allows you to accept your credits and share them via social media platforms.
Please remember that Bayesian network skills are in high demand these days, so don't delay in claiming and posting your credits!
Throughout the seminar, we alternate slide presentations and practical software demonstrations. We encourage a lively dialogue throughout the seminar, so there is plenty of opportunity for Q&A. Also, we'll have two coffee breaks for networking and offline questions.
The Seminar Program in Detail
Background & Theory
Structural Equation Modeling is a statistical technique for testing and estimating causal relations using a combination of statistical data and qualitative causal assumptions. Structural Equation Models (SEM) allow both confirmatory and exploratory modeling, meaning they are suited to both theory testing and theory development.
What we call Probabilistic Structural Equation Models (PSEMs) in BayesiaLab are conceptually similar to traditional SEMs. However, PSEMs are based on a Bayesian network structure as opposed to a series of equations. More specifically, PSEMs can be distinguished from SEMs in terms of key characteristics:
- All relationships in a PSEM are probabilistic—hence the name, as opposed to having deterministic relationships plus error terms in traditional SEMs.
- PSEMs are nonparametric, which facilitates the representation of nonlinear relationships, plus relationships between categorical variables.
- The structure of PSEMs is partially or fully machine-learned from data.
In general, specifying and estimating a traditional SEM requires a high degree of statistical expertise. Additionally, the multitude of manual steps involved can make the entire SEM workflow extremely time-consuming. The PSEM workflow in BayesiaLab, on the other hand, is accessible to non-statistician subject matter experts. Perhaps more importantly, it can be faster by several orders of magnitude. Finally, once a PSEM is validated, it can be utilized like any other Bayesian network. This means that the full array of analysis, simulation, and optimization tools is available to leverage the knowledge represented in the PSEM.
Case Study: Key Drivers Analysis from Consumer Survey Data
In this seminar, we present a prototypical PSEM application: key drivers analysis and product optimization based on consumer survey data. We examine how consumers perceive product attributes, and how these perceptions relate to the consumers’ purchase intent for specific products.
Given the inherent uncertainty of survey data, we also wish to identify higher-level variables, i.e. “latent” variables that represent concepts, which are not directly measured in the survey. We do so by analyzing the relationships between the so-called “manifest” variables, i.e. variables that are directly measured in the survey. Including such concepts helps in building more stable and reliable models than what would be possible using manifest variables only.
Our overall objective is making surveys clearer to interpret by researchers and making them “actionable” for managerial decision makers. The ultimate goal is to use the generated PSEM for prioritizing marketing and product initiatives to maximize purchase intent.
Frequently Asked Questions
What does it cost to participate?
Registration for this event is free of charge.
Is this a sales event?
This seminar is sponsored by Bayesia USA, and all software demos will feature BayesiaLab 6. However, the Bayesian network paradigm and theory of Structural Equation Modeling are entirely vendor-neutral topics. As such, the seminar will be relevant to researchers and practitioners who are not considering any new technology.
For those who are interested in learning more about BayesiaLab, we will certainly refer them to our ongoing course program and highlight other resources. Details about BayesiaLab licensing options and pricing will not be part of the presentation.
What educational background is required to understand the seminar program?
If you are proficient in college-level math and core statistical techniques, such as specifying and estimating multivariate regressions, you will find our seminar program useful. If you don't have this background, you will probably struggle with the seminar content. In other words, if math and statistics are not your strong suit, this event is probably not for you. This is not to discourage you from attending; we simply want to manage expectations so you will find this event to be a good use of your time.
How should I prepare for the seminar?
We recommend that you read the first three chapters of our book on Bayesian networks. You can download it for free via this link: bayesia.com/book. Also, Chapter 8 in the book will give you a good preview of the case study to be presented in the seminar.
Will the event be broadcast live?
No, you will need to by physically present to participate in the event. Also, the event will not be recorded.
Do I need to bring a computer?
No, you do not need to bring a computer. The instructor will present several practical examples during the seminar, but there will be not enough time for you to run these examples simultaneously during the event. However, you can obtain a BayesiaLab trial version afterward, so you can replicate the examples on your own.
Will you serve lunch at the event?
No, we will not serve a meal at the seminar. Please have lunch on your own beforehand. We'll have coffee available during the breaks.