Log Odds and the Interpretation of Logit Models
2017/05/30 by Edward C. Norton, Bryan E. Dowd, Bryan Dowd · 279 citations
Decision Sciences · Economics, Econometrics and Finance · Mathematics · Medicine · #Advanced Causal Inference Techniques #Computer science #Decision-Making and Behavioral Economics #Econometrics #Economic and Environmental Valuation #Interpretation (philosophy) #Logistic regression #Logit #Mathematics #Medicine #Odds #Statistics
paper · pdf · doi:10.1111/1475-6773.12712
published in Health Services Research 53(2), 859-878 (Wiley)
openalex publication_date 2017/05/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/04
Abstract
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.
Cited by
- When the party is over: Explaining the rise of the Spanish far-right SALF
- Better close to home? Geographical and socioeconomic constraints on gendered educational transitions at the upper secondary level
- Marginal Odds Ratios: What They Are, How to Compute Them, and Why Sociologists Might Want to Use Them
- Requiem for odds ratios
- Racial and Ethnic Disparities in Discharge Opioid Prescribing From a Hospital Medicine Service
- Mixed logit model and classification tree to investigate cyclists crash severity
- Legacy and Athlete Preferences at Harvard
- FormulaCompiler.jl and Margins.jl: Efficient Marginal Effects in Julia
- Association of Tobacco Control Policies With Youth Smoking Onset in Chile. [europepmc]
- Life Chaos is Associated with Reduced HIV Testing, Engagement in Care, and ART Adherence Among Cisgender Men and Transgender Women upon Entry into Jail. [europepmc]
- Financial Burdens of Cancer Treatment: A Systematic Review of Risk Factors and Outcomes. [europepmc]
- Association of Canada's Provincial Bans on Electronic Cigarette Sales to Minors With Electronic Cigarette Use Among Youths. [europepmc]
- The Affordable Care Act Medicaid Expansion and Smoking Cessation Among Low-Income Smokers. [europepmc]
- Association Between Physician Depressive Symptoms and Medical Errors: A Systematic Review and Meta-analysis. [europepmc]
- Hospitalisation and mortality in patients with comorbid COPD and heart failure: a systematic review and meta-analysis. [europepmc]
- Smallholder farmers' knowledge and willingness to pay for insect-based feeds in Kenya. [europepmc]
- Estimating Transition Probabilities from Published Evidence: A Tutorial for Decision Modelers. [europepmc]
- Transient Disruption of the Inferior Parietal Lobule Impairs the Ability to Attribute Intention to Action. [europepmc]
- Prevalence of and factors associated with unmet dental need among the US adult population in 2016. [europepmc]
- A cross-sectional study to determine factors affecting dental and medical students' preference for virtual learning during the COVID-19 outbreak. [europepmc]
- The Covid-19 pandemic and mental health of first-year college students: Examining the effect of Covid-19 stressors using longitudinal data. [europepmc]
- Changes in Magnetic Resonance Imaging Using the Prostate Cancer Radiologic Estimation of Change in Sequential Evaluation Criteria to Detect Prostate Cancer Progression for Men on Active Surveillance. [europepmc]
- Integrating gut microbiome and host immune markers to understand the pathogenesis of Clostridioides difficile infection. [europepmc]
- Role of inflammation in depression and anxiety: Tests for disorder specificity, linearity and potential causality of association in the UK Biobank. [europepmc]
- Racial and Ethnic Disparities in Discharge Opioid Prescribing From a Hospital Medicine Service. [europepmc]
- Association of Social Support With Functional Outcomes in Older Adults Who Live Alone. [europepmc]
- Application of two statistical approaches (Bayesian Kernel Machine Regression and Principal Component Regression) to assess breast cancer risk in association to exposure to mixtures of brominated flame retardants and per- and polyfluorinated alkylated substances in the E3N cohort. [europepmc]
- Shift work and the risk for metabolic syndrome among healthcare workers: A systematic review and meta-analysis. [europepmc]
- Association of emergency department crowding with inpatient outcomes. [europepmc]
- U.S. Population Data on Hearing Loss, Trouble Hearing, and Hearing-Device Use in Adults: National Health and Nutrition Examination Survey, 2011-12, 2015-16, and 2017-20. [europepmc]
- Predictive validity of the prognosis on admission aneurysmal subarachnoid haemorrhage scale for the outcome of patients with aneurysmal subarachnoid haemorrhage. [europepmc]
- Provision of Digital Health Technologies for Opioid Use Disorder Treatment by US Health Care Organizations. [europepmc]
- Validation of the accuracy of the modified World Federation of Neurosurgical Societies subarachnoid hemorrhage grading scale for predicting the outcomes of patients with aneurysmal subarachnoid hemorrhage. [europepmc]
Related