Observational data lends itself to analysis useful for large data sets, data that probably do not exhibit orthogonality and situations where we are interested in prediction rather than interpretation. The Generalized Regression platform is the place to build regression models for both designed experiments and observational data. Some things to keep in mind:
1) Penalized regression shows great promise for observational data.
2) Effect Heredity probably isn’t necessary.
3) Use a holdout set if you have enough data, otherwise the AICc.
See how to:
- Understand background principles related to estimation and the needs to consider:
- How far from the truth the estimates tend to be (Bias)
- How variable the estimates are (Variance)
- How bias and variance principles combined can be measured by Mean Square Error of an estimator
- Understand Penalized Regression techniques (Ridge, Lasso, Elastic Net, Adaptive Lasso, Double Lasso, Dantzig Selector)
- See how Effect Heredity is handled in JMP Pro
- Choose Grid Control options
- Use Forced Terms, Early Stopping and Informative Missing
Resources
