Services

Make the most of your investment in BIOVIA solutions with lab-to-plant process consulting, onsite implementation, expert training and superior support

Data Modeling Training

Overview and Audience

This course covers the use of Pipeline Pilot to perform statistical analysis and build models from your data. Topics include exploratory analysis, clustering, models of continuous data (regression models), and models of categorical data (classification models)

This course is a half-day class.

On completion of the workshop attendees should have the ability to modify and create complex data modeling protocols utilizing Pipeline Pilot’s Data Modeling tools.

Sample Agenda

  • Basic Statistics Components
  • Clustering
  • Regression Models for Continuous Properties
    • Least Squares
    • Partial Least Squares (PLS)
    • k-Nearest Neighbor (kNN)
  • Bayesian Classification Models
    • Theory
    • Using the Bayesian Learners
    • Applying a Bayesian Model
    • Evaluating the Model
    • Enrichment Plots
    • Viewing "Good" and "Bad" Features
    • Multiple Category Models
  • Recursive Partitioning Classification ModelsBayesian Classification Models
    • Single-Tree Models
    • Multi-Tree Forest Models
    • Recursive Partitioning versus Bayesian Learning

Browse By: