Learn more about experimental designs when influential factors have been identified and the goal is to optimize their levels. Principle underlying the construction of composite and Box-Behnken design are covered. Principle, model-building, and response surface methodology are reviewed.
Building a regression model with stats packages has become straightforward. However, interpreting the software output and building a good are no simple tasks. Learn about statistical modeling with a focus on linear models. What is a model? Estimating and interpreting model coefficients. Dealing with continuous and categorical predictors and interactions. Evaluating model performance: explanatory vs. predictive. Common pitfalls and best practices. Introduction to nonlinear regression.
Predictive analytics (PA) is on everyone's lips. But what is it really all about? Discover its principle, implementation, typical pitfalls and good practices. Learn about data wrangling and munging, a crucial step in predictive analytics. An overview of the most commonly used models is also presented.
Linear regression is inappropriate to model binary responses such as pass/fail, survived/died. Learn the principle of logistic regression part of the Generalized Linear Models along with its similarities with linear regression and its specific tools. Good practices for model-building and for assessing model goodness-of-fit are presented.
Classical linear regression is inappropriate when predictors are correlated - multicollinearity. Learn about Principal Component Regression (PCR) & Partial Least Squares (PLS) regression to deal with multicollinearity and when it is relevant to use them.
This module offers an overview of tree-based modeling techniques. Learn how they work, when to use them, their strengths and weaknesses, and their implementation including validation. Several real-life applications are presented.