Snug as a Bug: Goodness of Fit and Quality of Models

Research output: Contribution to journalArticle

4 Scopus citations

Abstract

In elucidating risk factors, or attempting to make predictions about the behavior of subjects in our biomedical studies, we often build statistical models. These models are meant to capture some aspect of reality, or some real-world process underlying the phenomena we are examining. However, no model is perfect, and it is thus important to have tools to assess how accurate models are. In this commentary, we delve into the various roles that our models can play. Then we introduce the notion of the goodness of fit of models and lay the ground work for further study of diagnostic tests for assessing both the fidelity of our models and the statistical assumptions underlying them.

Original languageEnglish (US)
Pages (from-to)1357-1360
Number of pages4
JournalJournal of Foot and Ankle Surgery
Volume56
Issue number6
DOIs
StatePublished - Nov 1 2017

    Fingerprint

Keywords

  • goodness of fit
  • parsimony
  • statistical modeling

ASJC Scopus subject areas

  • Surgery
  • Orthopedics and Sports Medicine

Cite this