Log Odds and the Interpretation of Logit Models

Details

• Personal Author:
  Dowd BE ; Norton EC
• Description:
  Objective: We discuss how to interpret coefficients from logit models, focusing on the importance of the standard deviation (σ) of the error term to that interpretation. Study Design: We show how odds ratios are computed, how they depend on the standard deviation (σ) of the error term, and their sensitivity to different model specifications. We also discuss alternatives to odds ratios. Principal Findings: There is no single odds ratio; instead, any estimated odds ratio is conditional on the data and the model specification. Odds ratios should not be compared across different studies using different samples from different populations. Nor should they be compared across models with different sets of explanatory variables. Conclusions: To communicate information regarding the effect of explanatory variables on binary {0,1} dependent variables, average marginal effects are generally preferable to odds ratios, unless the data are from a case-control study. [Description provided by NIOSH]
• Subjects:
  Epidemiology Occupational Health Risk Assessment Safety
• Keywords:
  Author Keywords: Logit Marginal Effects Mathematical Models Odds Ratio Probit Risk Analysis Risk Ratio Statistical Analysis Statistical Quality Control
• ISSN:
  0017-9124
• Document Type:
  Text
• Funding:
  Grant
• Genre:
  Journal Article
• Place as Subject:
  Massachusetts ; Michigan ; Minnesota ; OSHA Region 1 ; OSHA Region 5
• CIO:
  National Institute for Occupational Safety and Health (NIOSH)
• Topic:
  Workplace Safety & Health
• Location:
  North America
• Volume:
  53
• Issue:
  2
• NIOSHTIC Number:
  nn:20064236
• Citation:
  Health Serv Res 2018 Apr; 53(2):859-878
• Contact Point Address:
  Edward C. Norton, Ph.D., Department of Health Management and Policy, Department of Economics, M3108 SPH II, University of Michigan, Ann Arbor, MI 48109
• Email:
  ecnorton@umich.edu
• Federal Fiscal Year:
  2018
• Performing Organization:
  University of Minnesota Twin Cities
• Peer Reviewed:
  True
• Start Date:
  20050701
• Source Full Name:
  Health Services Research
• End Date:
  20250630
• Collection(s):
  National Institute for Occupational Safety and Health
• Main Document Checksum:
  urn:sha-512:b3b135b67b659f5c4ec1696d9bc26e3874b124dd476d9592be89fde02b052525da9e0a7a22f26658f4b91124e180a507966572d156f00a8241d0d6e6c432929a
• Download URL:
  https://stacks.cdc.gov/view/cdc/222737/cdc_222737_DS1.pdf
• File Type:
  [PDF - 301.77 KB ]