An evaluation of penalised survival methods for developing prognostic models with rare events
The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
Prognostic models for survival outcomes are often developed by fitting standard survival regression models, such as the Cox proportional hazards model, to representative datasets. However, these models can be unreliable if the datasets contain few events, which may be the case if either the disease or the event of interest is rare. Specific problems include predictions that are too extreme, and poor discrimination between low‐risk and high‐risk patients. The objective of this paper is to evaluate three existing penalised methods that have been proposed to improve predictive accuracy. In particular, ridge, lasso and the garotte, which use penalised maximum likelihood to shrink coefficient estimates and in some cases omit predictors entirely, are assessed using simulated data derived from two clinical datasets. The predictions obtained using these methods are compared with those from Cox models fitted using standard maximum likelihood. The simulation results suggest that Cox models fitted using maximum likelihood can perform poorly when there are few events, and that significant improvements are possible by taking a penalised modelling approach. The ridge method generally performed the best, although lasso is recommended if variable selection is required. Copyright © 2011 John Wiley & Sons, Ltd.
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
Relaxing the Rule of Ten Events per Variable in Logistic and Cox Regression
Vittinghoff, E., & McCulloch, C. E. (2007) · American Journal of Epidemiology · doi:10.1093/aje/kwk052 · Cited by 4,359 · cited 1×
“If the model involves estimation of a large number of parameters relative to the number of events, there is a risk of the model being over-fitted [5, 6].”
MethodThe Statistical Analysis of Failure Time Data
Kalbfleisch, J. D., & Prentice, R. L. (2002) · Wiley Series in Probability and Statistics · doi:10.1002/9781118032985 · Cited by 3,219
Peduzzi, P., Concato, J., Feinstein, A. R., & Holford, T. R. (1995) · Journal of Clinical Epidemiology · doi:10.1016/0895-4356(95)00048-8 · Cited by 2,154 · cited 2×
“This guideline suggests that an Events Per Variable (EPV) of at least 10, where EPV is the ratio of the number of events to the number of estimated regression coefficients, is required to achieve a reliable prognostic model [3,5,7].”
BackgroundMethodA new measure of prognostic separation in survival data
Royston, P., & Sauerbrei, W. (2004) · Statistics in Medicine · doi:10.1002/sim.1621 · Cited by 450 · cited 2×
“Calibration and discrimination were summarised visually using a plot based on prognostic separation [29].”
MethodApplication of Shrinkage Techniques in Logistic Regression Analysis: A Case Study
Steyerberg, E. W., Eijkemans, M. J. C., & Habbema, J. D. F. (2001) · Statistica Neerlandica · doi:10.1111/1467-9574.00157 · Cited by 124 · cited 2×
“Comparisons are made with the standard maximum likelihood approach with no variable selection, a backwards elimination procedure that is commonly used to reduce the number of predictors in a model, and a linear shrinkage technique that applies a single shrinkage factor to the maximum likelihood estimates after model f…”
Method
Cited by
Moons, K. G. M., Altman, D. G., Reitsma, J. B., Ioannidis, J. P. A., Macaskill, P., Steyerberg, E. W., Vickers, A. J., Ransohoff, D. F., & Collins, G. S. (2015) · Annals of Internal Medicine · doi:10.7326/m14-0698 · Cited by 5,147
O'Mahony, C., Jichi, F., Pavlou, M., Monserrat, L., Anastasakis, A., Rapezzi, C., Biagini, E., Gimeno, J. R., Limongelli, G., McKenna, W. J., et al. (2014) · European Heart Journal · doi:10.1093/eurheartj/eht439 · Cited by 1,251
Self-citationA calibration hierarchy for risk models was defined: from utopia to empirical data
Van Calster, B., Nieboer, D., Vergouwe, Y., De Cock, B., Pencina, M. J., & Steyerberg, E. W. (2016) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2015.12.005 · Cited by 910
How to develop a more accurate risk prediction model when there are few events
Pavlou, M., Ambler, G., Seaman, S. R., Guttmann, O., Elliott, P., King, M., & Omar, R. Z. (2015) · BMJ · doi:10.1136/bmj.h3868 · Cited by 664
Self-citationAdequate sample size for developing prediction models is not simply related to events per variable
Ogundimu, E. O., Altman, D. G., & Collins, G. S. (2016) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2016.02.031 · Cited by 546
Metadata
- Authors
- Ambler, G., Seaman, S., & Omar, R. Z.
- Venue
- Statistics in Medicine
- Publisher
- Wiley
- Published
- 2011-10-14
- Volume
- 31
- Issue
- 11-12
- Pages
- 1150-1161
- ISSN
- 0277-6715 (ISSN-L)
- 1097-0258
- OpenAlex
- W1965885948
- Cited by
- 107
- References
- 5
- FWCI
- 1.39
- Type
- journal article
- Language
- en
- Open access
- closed
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.