Skip to Content
Interactive Textbook on Clinical Symptom Research Logo


Home Button

Statistical Models for Prognostication
Author Bio
Introduction
Predictions: Statistical Models
Insight: Statistical Models
Ingredients: Statistical Models
Theoretical Aspects
Central Concepts
Currently selected section: Regression Models
Problems: Regression
Practical Advice
Example 1
Example 2
Chapter 8: Statistical Models for Prognostication: Development of Regression Models
        

You Answered:

Selection AWith stepwise selection and alpha=0.05.

INCORRECT

Usually the loss of information from omission of true predictors is larger than the gain by deleting noise variables. The correct answer is (b) or (c), using a higher p-value for selection does limit the loss of information due to omission of true predictors. A full model, including all covariables, may often lead to the best predictions from a model. This does require that the set of included candidate covariables is carefully chosen, e.g. based on empirical findings in other studies and clinical knowledge.

Back to Question