Dr. Peter Austin is a Senior Scientist at the Institute for Clinical Evaluative
Sciences (ICES) in Toronto, Canada, and a Professor in the department of Health Policy,
Management and Evaluation at the University of Toronto. His research interests include
statistical methods for the analysis of large health care databases, propensity-score
methods for causal inference, predictive models for cardiovascular outcomes, and
statistical methods for provider profiling. 

Propensity score methods

PDF

Using Ensemble-Based Methods for Directly Estimating Causal Effects: An Investigation of Tree-Based G-Computation, Multivariate Behavioral Research (2012)

Researchers are increasingly using observational or nonrandomized data to estimate causal treatment effects. Essential to...

 

PDF

An introduction to propensity-score methods for reducing confounding in observational studies, Multivariate Behavioral Research (2011)

The propensity score is the probability of treatment assignment conditional on observed baseline characteristics. The...

 

PDF

A Tutorial and Case Study in Propensity Score Analysis: An Application to Estimating the Effect of In-Hospital Smoking Cessation Counseling on Mortality, Multivariate Behavioral Research (2011)

Propensity score methods allow investigators to estimate causal treatment effects using observational or nonrandomized data....

 
A Tutorial on Methods to Estimating Clinically and Policy-Meaningful Measures of Treatment Effects in Prospective Observational Studies: A Review (with Andreas Laupacis), The International Journal of Biostatistics (2011)

In randomized controlled trials (RCTs), treatment assignment is unconfounded with baseline covariates, allowing outcomes to...

 

PDF

Comparing paired vs. non-paired statistical methods of analyses when making inferences about absolute risk reductions in propensity-score matched samples., Statistics in Medicine (2011)

Propensity-score matching allows one to reduce the effects of treatment-selection bias or confounding when estimating...

 

Predictive models

PDF

Using methods from the data-mining and machine-learning literature for disease classification and prediction: a case study examining classification of heart failure subtypes, Journal of Clinical Epidemiology (2013)

OBJECTIVE: Physicians classify patients into those with or without a specific disease. Furthermore, there is...

 

Link

Comparative ability of comorbidity classification methods for administrative data to predict outcomes in patients with chronic obstructive pulmonary disease, Annals of Epidemiology (2012)

PURPOSE: Administrative healthcare databases are used for health services research, comparative effectiveness studies, and measuring...

 

Link

Interpreting the concordance statistic of a logistic regression model: relation to the variance and odds ratio of a continuous explanatory variable, BMC Medical Research Methodology (2012)

Background: When outcomes are binary, the c-statistic (equivalent to the area under the Receiver Operating...

 

PDF

Regression trees for predicting mortality in patients with cardiovascular disease: what improvement is achieved by using ensemble-based methods?, Biometrical Journal (2012)

In biomedical research, the logistic regression model is the most commonly used method for predicting...

 

Link

Using the Johns Hopkins Aggregated Diagnosis Groups (ADGs) to predict mortality in a population-based cohort of subjects with schizophrenia in Ontario, Canada, Psychiatry Research (2012)

Administrative health care databases are increasingly used for health services and comparative effectiveness research. When...

 

Statistical methods for provider profiling

Estimating Multilevel Logistic Regression Models When the Number of Clusters is Low: A Comparison of Different Statistical Software Procedures, The International Journal of Biostatistics (2010)

Multilevel logistic regression models are increasingly being used to analyze clustered data in medical, public...

 

Link

Are (the log-odds of) Hospital Mortality Rates Normally Distributed in Ontario? Implications for Studying Variations in Outcomes of Medical Care, Journal of Evaluation in Clinical Practice (2009)

Objective: Hierarchical regression models are used to examine variations in outcomes following the provision of...

 

Link

Bayes Rules for Optimally using Hierarchical Regression Models to Identify High-mortality Hospitals, BMC Health Research Methodology (2008)

Background

There is a growing trend towards the production of "hospital report-cards" in which hospitals...

 

Link

Optimal Bayesian Probability Levels for Hospital Report Cards, Health Services and Outcomes Research Methodology (2008)

here is a growing trend towards the production of “hospital report-cards” in which hospitals with...

 

Link

Comparing Clinical Data with Administrative Data for Producing AMI Report Cards, Journal of the Royal Statistical Society – Series A (Statistics in Society). (2006)

We compared measures of hospital performance by using both administrative and clinical data sources. Hospital-specific...

 

Multilevel models for health services research

Estimating Multilevel Logistic Regression Models When the Number of Clusters is Low: A Comparison of Different Statistical Software Procedures, The International Journal of Biostatistics (2010)

Multilevel logistic regression models are increasingly being used to analyze clustered data in medical, public...

 

Link

Are (the log-odds of) Hospital Mortality Rates Normally Distributed in Ontario? Implications for Studying Variations in Outcomes of Medical Care, Journal of Evaluation in Clinical Practice (2009)

Objective: Hierarchical regression models are used to examine variations in outcomes following the provision of...

 

Link

Bias in Penalized Quasi-Likelihood Estimation in Random Effects Logistic Regression Models when the Random Effects are not Normally Distributed, Communications in Statistics – Simulation and Computation (2005)

Regression models incorporating random effects are being used with increasing frequency to examine variations in...

 

Link

Comparing hierarchical modeling with traditional logistic regression analysis among patients hospitalized with acute myocardial infarction: Should we be analyzing cardiovascular outcomes data differently?, American Heart Journal (2003)

Background: Data in health research are frequently structured hierarchically. For example, data may consist of...

 
An Introduction to Multilevel Regression Models, Canadian Journal of Public Health (2001)

Data in health research are frequently structured hierarchically. For example, data may consist of patients...

 

Randomized controlled trials

A Comparison of the Statistical Power of Different Methods for the Analysis of Repeated Cross-Sectional Cluster Randomization Trials with Binary Outcomes, The International Journal of Biostatistics (2010)

Repeated cross-sectional cluster randomization trials are cluster randomization trials in which the response variable is...

 

Link

A substantial and confusing variation exists in handling of baseline covariates in randomized controlled trials: a review of trials published in leading medical journals., Journal of Clinical Epidemiology (2010)

Objective: Statisticians have criticized the use of significance testing to compare the distribution of baseline...

 

Link

A comparison of the statistical power of different methods for the analysis of cluster randomization trials with binary outcomes, Statistics in Medicine (2007)

Cluster randomization trials are randomized controlled trials (RCTs) in which intact clusters of subjects are...

 

Link

Changes in Prescribing Patterns Following Publication of the ALLHAT Trial, Journal of the American Medical Association (2004)
 

Miscellaneous

The Mortality Risk Score and the ADG Score: two points-based scoring systems for the Johns Hopkins Aggregated Diagnosis Groups (ADGs) to predict mortality in a general adult population cohort in Ontario, Canada, Medical Care (2011)

Background: Logistic regression models that incorporated age, sex, and indicator variables for the Johns Hopkins’...

 
Using the Johns Hopkins Aggregated Diagnosis Groups (ADGs) to predict mortality in a general adult population cohort in Ontario, Canada, Medical Care (2011)

Background: Administrative health care databases are increasingly used for health services and comparative effectiveness research....

 

Link

A data-generation process for data with specified risk differences or numbers needed to treat, Communications in Statistics - Simulation and Computation (2010)

Monte Carlo simulation methods are increasingly being used to evaluate the performance of statistical methods...

 

Link

Using the standardized difference to compare the prevalence of a binary variable between two groups in observational research, Communications in Statistics – Simulation and Computation (2009)

Researchers are increasingly using the standardized difference to compare the distribution of baseline covariates between...

 

Link

Comparing clinical and administrative data for profiling hospitals on post-discharge medication use by AMI patients, American Heart Journal (2008)

Background

Postdischarge medication use is frequently used as a measure of hospital performance, with many...

 

Bayesian methods

Link

Bayesian Modeling of Missing Data in Clinical Research, Computational Statistics & Data Analysis (2005)

The issue of missing data frequently confronts researchers using data derived from patient medical records....

 

Link

A Comparison of Bayesian Methods for Profiling Hospital Performance, Medical Decision Making (2002)

There is a growing interest in the use of Bayesian methods for profiling institutional performance....

 

Link

Bayesian Extensions of the Tobit Model for Analyzing Measures of Health Status, Medical Decision Making (2002)

Self-reported health status is often measured using utility indices that provide a score intended to...

 

Link

Bayeswatch: An Overview of Bayesian Statistics, Journal of Evaluation in Clinical Practice (2002)

Increasingly, clinical research is evaluated on the quality of its statistical analysis. Traditionally, statistical analyses...

 

Link

A Comparison of a Bayesian versus a Frequentist Method for Profiling Hospital Performance, Journal of Evaluation in Clinical Practice (2001)

The objective of this study was to compare the classification of hospitals as outcomes outliers...

 

Regression methods

PDF

Using methods from the data-mining and machine-learning literature for disease classification and prediction: a case study examining classification of heart failure subtypes, Journal of Clinical Epidemiology (2013)

OBJECTIVE: Physicians classify patients into those with or without a specific disease. Furthermore, there is...

 

Link

Comparative ability of comorbidity classification methods for administrative data to predict outcomes in patients with chronic obstructive pulmonary disease, Annals of Epidemiology (2012)

PURPOSE: Administrative healthcare databases are used for health services research, comparative effectiveness studies, and measuring...

 

PDF

Regression trees for predicting mortality in patients with cardiovascular disease: what improvement is achieved by using ensemble-based methods?, Biometrical Journal (2012)

In biomedical research, the logistic regression model is the most commonly used method for predicting...

 

PDF

Using Ensemble-Based Methods for Directly Estimating Causal Effects: An Investigation of Tree-Based G-Computation, Multivariate Behavioral Research (2012)

Researchers are increasingly using observational or nonrandomized data to estimate causal treatment effects. Essential to...

 
A Tutorial on Methods to Estimating Clinically and Policy-Meaningful Measures of Treatment Effects in Prospective Observational Studies: A Review (with Andreas Laupacis), The International Journal of Biostatistics (2011)

In randomized controlled trials (RCTs), treatment assignment is unconfounded with baseline covariates, allowing outcomes to...

 

Health services research

Link

Comparative ability of comorbidity classification methods for administrative data to predict outcomes in patients with chronic obstructive pulmonary disease, Annals of Epidemiology (2012)

PURPOSE: Administrative healthcare databases are used for health services research, comparative effectiveness studies, and measuring...

 

Link

Using the Johns Hopkins Aggregated Diagnosis Groups (ADGs) to predict mortality in a population-based cohort of subjects with schizophrenia in Ontario, Canada, Psychiatry Research (2012)

Administrative health care databases are increasingly used for health services and comparative effectiveness research. When...

 
A Tutorial on Methods to Estimating Clinically and Policy-Meaningful Measures of Treatment Effects in Prospective Observational Studies: A Review (with Andreas Laupacis), The International Journal of Biostatistics (2011)

In randomized controlled trials (RCTs), treatment assignment is unconfounded with baseline covariates, allowing outcomes to...

 

PDF

Optimal caliper widths for propensity-score matching when estimating differences in means and differences in proportions in observational studies., Pharmaceutical Statistics (2011)

In a study comparing the effects of two treatments, the propensity score is the probability...

 
The Mortality Risk Score and the ADG Score: two points-based scoring systems for the Johns Hopkins Aggregated Diagnosis Groups (ADGs) to predict mortality in a general adult population cohort in Ontario, Canada, Medical Care (2011)

Background: Logistic regression models that incorporated age, sex, and indicator variables for the Johns Hopkins’...

 

Health related quality of life

Link

A Comparison of Methods for Analyzing Health Related Quality of Life Measures, Value in Health (2002)

Objectives: Self-reported health status is often measured using psychometric or utility indices that provide a...

 

Link

Bayesian Extensions of the Tobit Model for Analyzing Measures of Health Status, Medical Decision Making (2002)

Self-reported health status is often measured using utility indices that provide a score intended to...

 

Health Services Research

Link

Comparative ability of comorbidity classification methods for administrative data to predict outcomes in patients with chronic obstructive pulmonary disease, Annals of Epidemiology (2012)

PURPOSE: Administrative healthcare databases are used for health services research, comparative effectiveness studies, and measuring...

 

Link

Using the Johns Hopkins Aggregated Diagnosis Groups (ADGs) to predict mortality in a population-based cohort of subjects with schizophrenia in Ontario, Canada, Psychiatry Research (2012)

Administrative health care databases are increasingly used for health services and comparative effectiveness research. When...

 
A Tutorial on Methods to Estimating Clinically and Policy-Meaningful Measures of Treatment Effects in Prospective Observational Studies: A Review (with Andreas Laupacis), The International Journal of Biostatistics (2011)

In randomized controlled trials (RCTs), treatment assignment is unconfounded with baseline covariates, allowing outcomes to...

 

PDF

Optimal caliper widths for propensity-score matching when estimating differences in means and differences in proportions in observational studies., Pharmaceutical Statistics (2011)

In a study comparing the effects of two treatments, the propensity score is the probability...

 
The Mortality Risk Score and the ADG Score: two points-based scoring systems for the Johns Hopkins Aggregated Diagnosis Groups (ADGs) to predict mortality in a general adult population cohort in Ontario, Canada, Medical Care (2011)

Background: Logistic regression models that incorporated age, sex, and indicator variables for the Johns Hopkins’...

 

Computation

PDF

Generating survival times to simulate Cox proportional hazards models with time-varying covariates., Statistics in Medicine (2012)

Simulations and Monte Carlo methods serve an important role in modern statistical research. They allow...

 
Estimating Multilevel Logistic Regression Models When the Number of Clusters is Low: A Comparison of Different Statistical Software Procedures, The International Journal of Biostatistics (2010)

Multilevel logistic regression models are increasingly being used to analyze clustered data in medical, public...

 

General Biostatistics

PDF

Predictive accuracy of risk factors and markers: a simulation study of the effect of novel markers on different performance measures for logistic regression models, Statistics in Medicine (2013)

The change in c-statistic is frequently used to summarize the change in predictive accuracy when...

 

PDF

Comparing the cohort design and the nested case-control design in the presence of both time-invariant and time-dependent treatment and competing risks: bias and precision, Pharmacoepidemiology and Drug Safety (2012)

Purpose: Observational studies using electronic administrative health care databases are often used to estimate the...

 

PDF

Generating survival times to simulate Cox proportional hazards models with time-varying covariates., Statistics in Medicine (2012)

Simulations and Monte Carlo methods serve an important role in modern statistical research. They allow...

 

PDF

Using Ensemble-Based Methods for Directly Estimating Causal Effects: An Investigation of Tree-Based G-Computation, Multivariate Behavioral Research (2012)

Researchers are increasingly using observational or nonrandomized data to estimate causal treatment effects. Essential to...

 
A Tutorial on Methods to Estimating Clinically and Policy-Meaningful Measures of Treatment Effects in Prospective Observational Studies: A Review (with Andreas Laupacis), The International Journal of Biostatistics (2011)

In randomized controlled trials (RCTs), treatment assignment is unconfounded with baseline covariates, allowing outcomes to...

 

Epidemiology

Link

Comparative ability of comorbidity classification methods for administrative data to predict outcomes in patients with chronic obstructive pulmonary disease, Annals of Epidemiology (2012)

PURPOSE: Administrative healthcare databases are used for health services research, comparative effectiveness studies, and measuring...

 

PDF

Comparing the cohort design and the nested case-control design in the presence of both time-invariant and time-dependent treatment and competing risks: bias and precision, Pharmacoepidemiology and Drug Safety (2012)

Purpose: Observational studies using electronic administrative health care databases are often used to estimate the...

 
A Tutorial on Methods to Estimating Clinically and Policy-Meaningful Measures of Treatment Effects in Prospective Observational Studies: A Review (with Andreas Laupacis), The International Journal of Biostatistics (2011)

In randomized controlled trials (RCTs), treatment assignment is unconfounded with baseline covariates, allowing outcomes to...