Augmented Backward Elimination: A Pragmatic and Purposeful Way to Develop Statistical Models

• Published in: PloS one Vol. 9; no. 11; p. e113677
• Main Authors: Dunkler, Daniela, Plischke, Max, Leffondré, Karen, Heinze, Georg
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 21.11.2014; Public Library of Science (PLoS)
• Subjects: Algorithms; Biometrics; Computer simulation; Criteria; Empirical analysis; Epidemiology; Estimates; Hazards; Hypotheses; Informatics; Kidney diseases; Mathematical models; Medical statistics; Medicine and Health Sciences; Methods; Models, Statistical; Physical Sciences; Regression analysis; Regression coefficients; Research and Analysis Methods; Statistical analysis; Statistical modelling; Statistical models; Studies; Survival analysis

Statistical models are simple mathematical rules derived from empirical data describing the association between an outcome and several explanatory variables. In a typical modeling situation statistical analysis often involves a large number of potential explanatory variables and frequently only part...