The DOI matches its Crossref record; 45 of the 45 references it cites were found in a registry or an index.
Separation in Logistic Regression: Causes, Consequences, and Control
Open accessAbstract
Separation is encountered in regression models with a discrete outcome (such as logistic regression) where the covariates perfectly predict the outcome. It is most frequent under the same conditions that lead to small-sample and sparse-data bias, such as presence of a rare outcome, rare exposures, highly correlated covariates, or covariates with strong effects. In theory, separation will produce infinite estimates for some coefficients. In practice, however, separation may be unnoticed or mishandled because of software limits in recognizing and handling the problem and in notifying the user. We discuss causes of separation in logistic regression and describe how common software packages deal with it. We then describe methods that remove separation, focusing on the same penalized-likelihood techniques used to address more general sparse-data problems. These methods improve accuracy, avoid software problems, and allow interpretation as Bayesian analyses with weakly informative priors. We discuss likelihood penalties, including some that can be implemented easily with any software package, and their relative advantages and disadvantages. We provide an illustration of ideas and methods using data from a case-control study of contraceptive practices and urinary tract infection.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Regression shrinkage and selection via the lasso
Tibshirani, R. (1996) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1996.tb02080.x · Cited by 51,482
The Elements of Statistical Learning
Hastie, T., Tibshirani, R., & Friedman, J. (2009) · Springer Series in Statistics · doi:10.1007/978-0-387-84858-7 · Cited by 25,970
The Elements of Statistical Learning
Hastie, T., Friedman, J., & Tibshirani, R. (2001) · Springer Series in Statistics · doi:10.1007/978-0-387-21606-5 · Cited by 24,162
Regularization Paths for Generalized Linear Models via Coordinate Descent
Friedman, J., Hastie, T., & Tibshirani, R. (2010) · Journal of Statistical Software · doi:10.18637/jss.v033.i01 · Cited by 19,927
Harrell (2015) · Springer Series in Statistics · doi:10.1007/978-3-319-19425-7 · Cited by 6,878
Bias reduction of maximum likelihood estimates
FIRTH, D. (1993) · Biometrika · doi:10.1093/biomet/80.1.27 · Cited by 5,035
Clinical Prediction Models: A Practical Approach to Development, Validation, and Updating
Steyerberg, E. W. (2019) · Statistics for Biology and Health · doi:10.1007/978-3-030-16399-0 · Cited by 3,281
A solution to the problem of separation in logistic regression
Heinze, G., & Schemper, M. (2002) · Statistics in Medicine · doi:10.1002/sim.1047 · Cited by 2,711
Self-citationShmueli, G. (2010) · Statistical Science · doi:10.1214/10-sts330 · Cited by 2,517
(2010) · Encyclopedia of Research Design · doi:10.4135/9781412961288.n40 · Cited by 1,995
A weakly informative default prior distribution for logistic and other regression models
Gelman, A., Jakulin, A., Pittau, M. G., & Su, Y.-S. (2008) · The Annals of Applied Statistics · doi:10.1214/08-aoas191 · Cited by 1,790
Ridge Estimators in Logistic Regression
Cessie, S. L., & Houwelingen, J. C. V. (1992) · Applied Statistics · doi:10.2307/2347628 · Cited by 1,680
A WEAKLY INFORMATIVE DEFAULT PRIOR DISTRIBUTION FOR LOGISTIC AND OTHER REGRESSION MODELS
Gelman, A., Jakulin, A., & Grazia, M. (2009) · Cited by 1,352
On the existence of maximum likelihood estimates in logistic regression models
ALBERT, A., & ANDERSON, J. A. (1984) · Biometrika · doi:10.1093/biomet/71.1.1 · Cited by 1,153
Sparse data bias: a problem hiding in plain sight
Greenland, S., Mansournia, M. A., & Altman, D. G. (2016) · BMJ · doi:10.1136/bmj.i1981 · Cited by 898
Self-citationClinical Prediction Models: A Practical Approach to Development, Validation and Updating
Mann, C. J. H. (2009) · Kybernetes · doi:10.1108/k.2009.06738fae.002 · Cited by 783
Firth's logistic regression with rare events: accurate effect estimates and predictions?
Puhr, R., Heinze, G., Nold, M., Lusa, L., & Geroldinger, A. (2017) · Statistics in Medicine · doi:10.1002/sim.7273 · Cited by 483
Self-citationA Solution to the Problem of Monotone Likelihood in Cox Regression
Heinze, G., & Schemper, M. (2001) · Biometrics · doi:10.1111/j.0006-341x.2001.00114.x · Cited by 396
Self-citationHeinze, G. (2006) · Statistics in Medicine · doi:10.1002/sim.2687 · Cited by 379
Self-citationProblems due to Small Samples and Sparse Data in Conditional Logistic Regression Analysis
Greenland, S., Schwartzbaum, J. A., & Finkle, W. D. (2000) · American Journal of Epidemiology · doi:10.1093/oxfordjournals.aje.a010240 · Cited by 370
Self-citationLesaffre, E., & Lawson, A. B. (2012) · Wiley eBooks · doi:10.1002/9781119942412 · Cited by 303
THE FALLACY OF EMPLOYING STANDARDIZED REGRESSION COEFFICIENTS AND CORRELATIONS AS MEASURES OF EFFECT
GREENLAND, S., SCHLESSELMAN, J. J., & CRIQUI, M. H. (1986) · American Journal of Epidemiology · doi:10.1093/oxfordjournals.aje.a114229 · Cited by 256
Self-citationGreenland, S., & Mansournia, M. A. (2015) · Statistics in Medicine · doi:10.1002/sim.6537 · Cited by 237
Self-citationMaximum Likelihood, Profile Likelihood, and Penalized Likelihood: A Primer
Cole, S. R., Chu, H., & Greenland, S. (2014) · American Journal of Epidemiology · doi:10.1093/aje/kwt245 · Cited by 215
Self-citationBias reduction in exponential family nonlinear models
Kosmidis, I., & Firth, D. (2009) · Biometrika · doi:10.1093/biomet/asp055 · Cited by 204
Bayesian perspectives for epidemiological research. II. Regression analysis
Greenland, S. (2007) · International Journal of Epidemiology · doi:10.1093/ije/dyl289 · Cited by 201
Self-citation(2012) · SpringerReference · doi:10.1007/springerreference_205246 · Cited by 168
Poisson: Some Convergence Issues
Silva, J. M. C. S., & Tenreyro, S. (2011) · The Stata Journal Promoting communications on statistics and Stata · doi:10.1177/1536867x1101100203 · Cited by 164
Rahman, M. S., & Sultana, M. (2017) · BMC Medical Research Methodology · doi:10.1186/s12874-017-0313-9 · Cited by 139
Standardized Regression Coefficients: A Further Critique and Review of Some Alternatives
Greenland, S., Maclure, M., Schlesselman, J. J., Poole, C., & Morgenstern, H. (1991) · Epidemiology · doi:10.1097/00001648-199109000-00015 · Cited by 138
Self-citationBias‐reduced and separation‐proof conditional logistic regression with small or sparse data sets
Heinze, G., & Puhr, R. (2010) · Statistics in Medicine · doi:10.1002/sim.3794 · Cited by 135
Self-citationStandardized regression coefficients: a further critique and review of some alternatives.
Greenland, S., Maclure, M., Schlesselman, J. J., Poole, C., & Morgenstern, H. (1991) · PubMed · Cited by 124
Self-citationBias correction in maximum likelihood logistic regression
Schaefer, R. L. (1983) · Statistics in Medicine · doi:10.1002/sim.4780020108 · Cited by 94
Median Unbiased Estimation for Binary Data
Hirji, K. F., Tsiatis, A. A., & Mehta, C. R. (1989) · The American Statistician · doi:10.1080/00031305.1989.10475597 · Cited by 93
Bayesian regression in SAS software
Sullivan, S. G., & Greenland, S. (2012) · International Journal of Epidemiology · doi:10.1093/ije/dys213 · Cited by 87
Self-citationA permutation test for inference in logistic regression with small‐ and moderate‐sized data sets
Potter, D. M. (2005) · Statistics in Medicine · doi:10.1002/sim.1931 · Cited by 86
On the Use of Wald's Test in Exponential Families
Væth, M., & Væth, M. (1985) · International Statistical Review · doi:10.2307/1402935 · Cited by 82
Generalized Conjugate Priors for Bayesian Analysis of Risk and Survival Regressions
Greenland, S. (2003) · Biometrics · doi:10.1111/1541-0420.00011 · Cited by 52
Self-citationApproximate Bayesian Logistic Regression via Penalized Likelihood by Data Augmentation
Discacciati, A., Orsini, N., & Greenland, S. (2015) · The Stata Journal Promoting communications on statistics and Stata · doi:10.1177/1536867x1501500306 · Cited by 47
Self-citationA comparative study of the bias corrected estimates in logistic regression
Maiti, T., & Pradhan, V. (2008) · Statistical Methods in Medical Research · doi:10.1177/0962280207084156 · Cited by 45
Condom Use and First-Time Urinary Tract Infection
Foxman, B., Marsh, J., Gillespie, B. W., Rubin, N., Koopman, J. S., & Spear, S. J. (1997) · Epidemiology · doi:10.1097/00001648-199710000-00004 · Cited by 43
Salama, M. M., Andrukhova, O., Hoda, M. A., Taghavi, S., Jaksch, P., Heinze, G., Klepetko, W., & Aharinejad, S. (2010) · American Journal of Transplantation · doi:10.1111/j.1600-6143.2009.02957.x · Cited by 39
Self-citationJACKKNIFE BIAS REDUCTION FOR POLYCHOTOMOUS LOGISTIC REGRESSION
Bull, S. B., Greenwood, C. M. T., & Hauck, W. W. (1997) · Statistics in Medicine · Cited by 22
On bias reduction in exponential and non-exponential family regression models
Cordeiro, G. M., & Cribari‐Neto, F. (1998) · Communications in Statistics - Simulation and Computation · doi:10.1080/03610919808813491 · Cited by 19
Heinze, G. (2012) · Statistical Methods in Medical Research · doi:10.1177/0962280212440533 · Cited by 2
Self-citation
Cited by
Mansournia, M. A., Collins, G. S., Nielsen, R. O., Nazemipour, M., Jewell, N. P., Altman, D. G., & Campbell, M. J. (2021) · British Journal of Sports Medicine · doi:10.1136/bjsports-2020-103652 · Cited by 263
Self-citationCase-control matching: effects, misconceptions, and recommendations
Mansournia, M. A., Jewell, N. P., & Greenland, S. (2018) · European Journal of Epidemiology · doi:10.1007/s10654-017-0325-0 · Cited by 175
Self-citationVan Calster, B., van Smeden, M., De Cock, B., & Steyerberg, E. W. (2020) · Statistical Methods in Medical Research · doi:10.1177/0962280220921415 · Cited by 120
“In this way, we could avoid the exclusion of samples that were suggestive of separation.(34) For logistic regression with bootstrap uniform shrinkage, bootstrap models suggestive of separation were replaced by other bootstrap replicates without separation.”
Method(2025) · doi:10.1145/3706598.3713371 · Cited by 1
Metadata
- Authors
- Mansournia, M. A., Geroldinger, A., Greenland, S., & Heinze, G.
- Venue
- American Journal of Epidemiology
- Publisher
- Oxford University Press (OUP)
- Published
- 2017-08-17
- Volume
- 187
- Issue
- 4
- Pages
- 864-870
- ISSN
- 0002-9262 (ISSN-L)
- 1476-6256
- OpenAlex
- W2747812981
- Cited by
- 296
- References
- 45
- FWCI
- 12.06
- Type
- journal article
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.