Advanced search
Publication Cover
The American Statistician Volume 58, 2004 - Issue 2
Submit an article Journal homepage
1,700
Views
418
CrossRef citations to date
0
Altmetric
Primary Article

Bootstrap Methods for Developing Predictive Models

Peter C Austin Peter C. Austin is Scientist, Institute for Clinical Evaluative Sciences, G1 06, 2075 Bayview Avenue, Toronto, Ontario, M4N 3M5 Canada . Austin is also affiliated with the Department of Public Health Sciences, University of Toronto, Toronto, Ontario; and Department of Health Policy, Management and Evaluation, University of Toronto. Jack V. Tu is Senior Scientist, Institute for Clinical Evaluative Sciences, Toronto, Ontario, Canada; also affiliated with the Department of Public Health Sciences, University of Toronto, Toronto, Ontario; Department of Health Policy, Management, and Evaluation, University of Toronto; Clinical Epidemiology and Health Care Research Program (Sunnybrook and Women's College Site); and Division of General Internal Medicine, Sunnybrookand Women's College Health Sciences Centre and the University of Toronto. The views expressed herein are solely those of the authors and do not represent the views of any of the sponsoring organizations. The Institute for Clinical Evaluative Sciences (ICES) is supported in part by a grant from the Ontario Ministry of Health and Long-Term Care. The opinions, results, and conclusions are those of the authors and no endorsement by the Ministry of Health and Long-Term Care or by the Institute for Clinical Evaluative Sciences is intended or should be inferred. This research was supported in part by an operating grant from the Canadian Institutes of Health Research (CIHR). Austin is supported in part by a New Investigator Award from the CIHR (Institute of Health Services and Policy Research). Tu is supported by a Canada Research Chair in Health Services Research.
&
Jack V Tu Peter C. Austin is Scientist, Institute for Clinical Evaluative Sciences, G1 06, 2075 Bayview Avenue, Toronto, Ontario, M4N 3M5 Canada . Austin is also affiliated with the Department of Public Health Sciences, University of Toronto, Toronto, Ontario; and Department of Health Policy, Management and Evaluation, University of Toronto. Jack V. Tu is Senior Scientist, Institute for Clinical Evaluative Sciences, Toronto, Ontario, Canada; also affiliated with the Department of Public Health Sciences, University of Toronto, Toronto, Ontario; Department of Health Policy, Management, and Evaluation, University of Toronto; Clinical Epidemiology and Health Care Research Program (Sunnybrook and Women's College Site); and Division of General Internal Medicine, Sunnybrookand Women's College Health Sciences Centre and the University of Toronto. The views expressed herein are solely those of the authors and do not represent the views of any of the sponsoring organizations. The Institute for Clinical Evaluative Sciences (ICES) is supported in part by a grant from the Ontario Ministry of Health and Long-Term Care. The opinions, results, and conclusions are those of the authors and no endorsement by the Ministry of Health and Long-Term Care or by the Institute for Clinical Evaluative Sciences is intended or should be inferred. This research was supported in part by an operating grant from the Canadian Institutes of Health Research (CIHR). Austin is supported in part by a New Investigator Award from the CIHR (Institute of Health Services and Policy Research). Tu is supported by a Canada Research Chair in Health Services Research.
Pages 131-137 | Published online: 01 Jan 2012
 
Sample our Mathematics & Statistics journals, sign in here to start your FREE access for 14 days

Abstract

Researchers frequently use automated model selection methods such as backwards elimination to identify variables that are independent predictors of an outcome under consideration. We propose using bootstrap resampling in conjunction with automated variable selection methods to develop parsimonious prediction models. Using data on patients admitted to hospital with a heart attack, we demonstrate that selecting those variables that were identified as independent predictors of mortality in at least 60%% of the bootstrap samples resulted in a parsimonious model with excellent predictive ability.

Reprints and Corporate Permissions

Please note: Selecting permissions does not provide access to the full text of the article, please see our help page How do I view content?

To request a reprint or corporate permissions for this article, please click on the relevant link below:

Order Reprints Request Corporate Permissions

Academic Permissions

Please note: Selecting permissions does not provide access to the full text of the article, please see our help page How do I view content?

Obtain permissions instantly via Rightslink by clicking on the button below:

Request Academic Permissions

If you are unable to obtain permissions via Rightslink, please complete and submit this Permissions form. For more information, please visit our Permissions help page.

Related Research Data

Wood density, growth and mortality relationships of lianas on environmental gradients in fragmented forests of montane landscapes
Source: Wiley
Projected range contractions of montane biodiversity under global warming
Source: The Royal Society
Supplementing Claims Data with Electronic Medical Records to Improve Estimation and Classification of Rheumatoid Arthritis Disease Activity: A Machine Learning Approach.
Source: Wiley
Mapping, bayesian geostatistical analysis and spatial prediction of lymphatic filariasis prevalence in Africa.
Source: Public Library of Science (PLoS)
Combining Individual Phenotypes of Feed Intake With Genomic Data to Improve Feed Efficiency in Sea Bass.
Source: Frontiers Media SA
Personalized prediction of antidepressant v. placebo response: evidence from the EMBARC study.
Source: Cambridge University Press (CUP)
Increased frequency of extreme Indian Ocean Dipole events due to greenhouse warming
Source: Springer Science and Business Media LLC
Does hyperthermic intraoperative chemotherapy lead to improved outcomes in patients with ovarian cancer? A single center cohort study in 111 consecutive patients
Source: Springer Science and Business Media LLC
Estimating daily air temperatures over the Tibetan Plateau by dynamically integrating MODIS LST data
Source: American Geophysical Union (AGU)
Survival to Stage II with Ventricular Dysfunction: Secondary Analysis of the Single Ventricle Reconstruction Trial
Source: Springer Science and Business Media LLC
Predicting Incident Radiographic Knee Osteoarthritis in Middle-Aged Women Within Four Years: The Importance of Knee-Level Prognostic Factors
Source: Wiley
More-frequent extreme northward shifts of eastern Indian Ocean tropical convergence under greenhouse warming.
Source: Springer Science and Business Media LLC
Prognostic Models for Predicting Overall Survival in Patients with Primary Gastric Cancer: A Systematic Review
Source: Hindawi Limited
Incidence of and risk factors for falls among adults
Source: Wiley
Urbanization and agricultural productivity: some lessons from European cities
Source: HAL CCSD
Flexibility in phenology and habitat use act as buffers to long-term population declines in UK passerines
Source: Wiley
Low, rather than High, Body Mass Index Is a Risk Factor for Acute Kidney Injury in Multiethnic Asian Patients: A Retrospective Observational Study.
Source: Hindawi
Weather conditions conducive to Beijing severe haze more frequent under climate change
Source: Springer Science and Business Media LLC
Rates and predictors of recurrent work disability due to common mental health disorders in the United States
Source: Public Library of Science (PLoS)
Coprophenomena in Tourette syndrome.
Source: Wiley
Two Types of Flash Drought and Their Connections with Seasonal Drought
Source: (:unav)
Neutrophil Count Is Associated With Reduced Gray Matter and Enlarged Ventricles in First-Episode Psychosis.
Source: Oxford University Press (OUP)
SMART-COP: A Tool for Predicting the Need for Intensive Respiratory or Vasopressor Support in Community-Acquired Pneumonia
Source: Oxford University Press (OUP)
Spatio‐temporal patterns of fish assemblages in a large regulated alluvial river
Source: HAL CCSD
Risk and prognostic nomograms for hepatocellular carcinoma with newly-diagnosed pulmonary metastasis using SEER data.
Source: PeerJ
Increasing frequency of extreme El Niño events due to greenhouse warming
Source: HAL CCSD
The relationship between ICU hypotension and in-hospital mortality and morbidity in septic patients.
Source: Springer Science and Business Media LLC
Modeling of an integrative prototype based on genetic, phenotypic, and environmental information for personalized prescription of energy-restricted diets in overweight/obese subjects.
Source: Oxford University Press (OUP)
Colorectal Cancer Screening Follow-Up
Source: Wiley
A Vulnerability Risk Index of Self‐Neglect in a Community‐Dwelling Older Population
Source: Wiley
Preferential selection of categorical variables in bootstrap samples
Source: Wiley
Predicting long-term survival after coronary artery bypass graft surgery.
Source: Oxford University Press (OUP)
Predicting the Occurrence of Postoperative Distal Junctional Kyphosis in Cervical Deformity Patients
Source: Oxford University Press (OUP)
CXCL9 and Kidney Transplant Outcomes
Source: Wiley
The use of geographic information system and 1860s cadastral data to model agricultural suitability before heavy mechanization. A case study from Malta.
Source: PLOS
Using connectivity metrics and niche modelling to explore the occurrence of the northern crested newt Triturus cristatus (Amphibia, Caudata) in a traditionally managed landscape
Source: Cambridge University Press (CUP)

Linking provided by 

Related research

People also read lists articles that other readers of this article have read.

Recommended articles lists articles that we recommend and is powered by our AI driven recommendation engine.

Cited by lists all citing articles based on Crossref citations.
Articles with the Crossref icon will open in a new tab.