The Binary Regression Quantile Plot: Assessing the Importance of Predictors in Binary Regression Visually

Bura, Efstathia; Gastwirth, Joseph L.

doi:10.1002/1521-4036(200102)43:1<5::aid-bimj5>3.0.co;2-6

Cited by 43 publications

(60 citation statements)

References 10 publications

(8 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Therefore, the AARD can also be interpreted as a Kolmogorov-Smirnov distance between the case and control risk distributions. Finally, Huang and Pepe [10] and Gu and Pepe [7] showed that the standardized total gain statistic proposed by Bura and Gastwirth [2] as a measure of predictive capacity of a model risk(X), sT G = |risk(X) − ρ|dF (X)/2ρ(1 − ρ) is equal to the AARD.…”

Section: Measures Independent Of Risk Thresholdsmentioning

confidence: 99%

Methods for Evaluating Prediction Performance of Biomarkers and Tests

Pepe

Janes

2013

Risk Assessment and Evaluation of Predictions

View full text Add to dashboard Cite

Section: Measures Independent Of Risk Thresholdsmentioning

confidence: 99%

Methods for Evaluating Prediction Performance of Biomarkers and Tests

Pepe

Janes

2013

Risk Assessment and Evaluation of Predictions

View full text Add to dashboard Cite

“…Total gain, proposed by Bura and Gastwirth (2001) is defined as , marker assigning risk(Y ) = ρ to all subjects. TG is appealing because it can be visualized directly from the predictiveness curve.…”

Section: Total Gainmentioning

confidence: 99%

“…Bura and Gastwirth (2001) used the risk quantiles, R(ν), to assess predictors in binary regression models. They proposed a summary index which they called the total gain.…”

Section: Introductionmentioning

confidence: 99%

“…These include measures derived 1 Gu and Pepe: Markers for Prediction Unauthenticated Download Date | 5/11/18 6:02 AM from the receiver operating characteristic (ROC) curve and the Lorenz curve, predictive values, misclassification rates, and measures of explained variation. Bura and Gastwirth (2001) used the risk quantiles, R(ν), to assess predictors in binary regression models. They proposed a summary index which they called the total gain.…”

mentioning

confidence: 97%

See 1 more Smart Citation

Measures to Summarize and Compare the Predictive Capacity of Markers

Gu¹,

Pepe²

2009

The International Journal of Biostatistics

View full text Add to dashboard Cite

The predictive capacity of a marker in a population can be described using the population distribution of risk (Huang et al. 2007;Pepe et al. 2008a;Stern 2008). Virtually all standard statistical summaries of predictability and discrimination can be derived from it (Gail and Pfeiffer 2005). The goal of this paper is to develop methods for making inference about risk prediction markers using summary measures derived from the risk distribution. We describe some new clinically motivated summary measures and give new interpretations to some existing statistical measures. Methods for estimating these summary measures are described along with distribution theory that facilitates construction of confidence intervals from data. We show how markers and, more generally, how risk prediction models, can be compared using clinically relevant measures of predictability. The methods are illustrated by application to markers of lung function and nutritional status for predicting subsequent onset of major pulmonary infection in children suffering from cystic fibrosis. Simulation studies show that methods for inference are valid for use in practice. KEYWORDS: discrimination, risk, classification, decision makingAuthor Notes: This work is supported in part by grants from the National Institutes of Health (R01 GM054438 and U01 CA086368).Unauthenticated Download Date | 5/11/18 6:02 AMThe predictive capacity of a marker in a population can be described using the population distribution of risk (Huang et al. 2007;Pepe et al. 2008a;Stern 2008). Virtually all standard statistical summaries of predictability and discrimination can be derived from it (Gail and Pfeiffer 2005). The goal of this paper is to develop methods for making inference about risk prediction markers using summary measures derived from the risk distribution. We describe some new clinically motivated summary measures and give new interpretations to some existing statistical measures. Methods for estimating these summary measures are described along with distribution theory that facilitates construction of confidence intervals from data. We show how markers and, more generally, how risk prediction models, can be compared using clinically relevant measures of predictability. The methods are illustrated by application to markers of lung function and nutritional status for predicting subsequent onset of major pulmonary infection in children suffering from cystic fibrosis. Simulation studies show that methods for inference are valid for use in practice. BackgroundLet D denote a binary outcome variable, such as presence of disease or occurrence of an event within a specified time period and let Y denote a set of predictive markers used to predict a bad outcome, D = 1, or a good outcome, D = 0. For example, elements of the Framingham risk score (age, gender, total and high-density lipoprotein cholesterol, systolic blood pressure, treatment for hypertension and smoking) are used to predict occurrence of a cardiovascular event within 10 years (http://hp2010.nhlbihin.net/...

show abstract

“…The eAppendix relates MRS to many statistics, including discretized versions of statistics used 129 for continuous biomarkers [18][19][20][21][22] For a perfect test (PPV=1 and cNPV=0), the equation for MRS (1) reveals that the 156 maximum MRS is 50%, which occurs when disease prevalence and test positivity are both 50%. 157…”

Section: And the Area 61mentioning

confidence: 99%