Two Paradoxes in Linear Regression Analysis

Regression is one of the favorite tools in applied statistics. However, misuse and misinterpretation of results from regression analysis are common in biomedical research. In this paper we use statistical theory and simulation studies to clarify some paradoxes around this popular statistical method....

Descripción completa

Detalles Bibliográficos
Autores principales: FENG, Ge, PENG, Jing, TU, Dongke, ZHENG, Julia Z., FENG, Changyong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Shanghai Municipal Bureau of Publishing 2016
Materias:
Biostatistics in Psychiatry (36)
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5434296/
https://www.ncbi.nlm.nih.gov/pubmed/28638214
http://dx.doi.org/10.11919/j.issn.1002-0829.216084
Descripción
Sumario:Regression is one of the favorite tools in applied statistics. However, misuse and misinterpretation of results from regression analysis are common in biomedical research. In this paper we use statistical theory and simulation studies to clarify some paradoxes around this popular statistical method. In particular, we show that a widely used model selection procedure employed in many publications in top medical journals is wrong. Formal procedures based on solid statistical theory should be used in model selection.

Ejemplares similares