Nonparametric predictive inference with parametric copulas for combining bivariate diagnostic tests
Measuring the accuracy of diagnostic tests is crucial in many application areas including medicine, machine learning and credit scoring. The receiver operating characteristic (ROC) curve is a useful tool to assess the ability of a diagnostic test to discriminate among two classes or groups. In pract...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
International Academic Press
2018
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/22880/ http://umpir.ump.edu.my/id/eprint/22880/1/SOIC-FC-1708.pdf |
| _version_ | 1848821672919957504 |
|---|---|
| author | Noryanti, Muhammad Coolen-Maturi, Tahani Coolen, Frank PA |
| author_facet | Noryanti, Muhammad Coolen-Maturi, Tahani Coolen, Frank PA |
| author_sort | Noryanti, Muhammad |
| building | UMP Institutional Repository |
| collection | Online Access |
| description | Measuring the accuracy of diagnostic tests is crucial in many application areas including medicine, machine learning and credit scoring. The receiver operating characteristic (ROC) curve is a useful tool to assess the ability of a diagnostic test to discriminate among two classes or groups. In practice, multiple diagnostic tests or biomarkers may be combined to improve diagnostic accuracy, e.g. by maximizing the area under the ROC curve. In this paper we present Nonparametric Predictive Inference (NPI) for best linear combination of two biomarkers, where the dependence of the two biomarkers is modelled using parametric copulas. NPI is a frequentist statistical method that is explicitly aimed at using few modelling assumptions, enabled through the use of lower and upper probabilities to quantify uncertainty. The combination of NPI for the individual biomarkers, combined with a basic parametric copula to take dependence into account, has good robustness properties and leads to quite straightforward computation. We briefly comment on the results of a simulation study to investigate the performance of the proposed method in comparison to the empirical method. An example with data from the literature is provided to illustrate the proposed method, and related research problems are briefly discussed. |
| first_indexed | 2025-11-15T02:29:05Z |
| format | Article |
| id | ump-22880 |
| institution | Universiti Malaysia Pahang |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T02:29:05Z |
| publishDate | 2018 |
| publisher | International Academic Press |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | ump-228802019-01-16T08:21:08Z http://umpir.ump.edu.my/id/eprint/22880/ Nonparametric predictive inference with parametric copulas for combining bivariate diagnostic tests Noryanti, Muhammad Coolen-Maturi, Tahani Coolen, Frank PA Q Science (General) QA Mathematics Measuring the accuracy of diagnostic tests is crucial in many application areas including medicine, machine learning and credit scoring. The receiver operating characteristic (ROC) curve is a useful tool to assess the ability of a diagnostic test to discriminate among two classes or groups. In practice, multiple diagnostic tests or biomarkers may be combined to improve diagnostic accuracy, e.g. by maximizing the area under the ROC curve. In this paper we present Nonparametric Predictive Inference (NPI) for best linear combination of two biomarkers, where the dependence of the two biomarkers is modelled using parametric copulas. NPI is a frequentist statistical method that is explicitly aimed at using few modelling assumptions, enabled through the use of lower and upper probabilities to quantify uncertainty. The combination of NPI for the individual biomarkers, combined with a basic parametric copula to take dependence into account, has good robustness properties and leads to quite straightforward computation. We briefly comment on the results of a simulation study to investigate the performance of the proposed method in comparison to the empirical method. An example with data from the literature is provided to illustrate the proposed method, and related research problems are briefly discussed. International Academic Press 2018 Article PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/22880/1/SOIC-FC-1708.pdf Noryanti, Muhammad and Coolen-Maturi, Tahani and Coolen, Frank PA (2018) Nonparametric predictive inference with parametric copulas for combining bivariate diagnostic tests. Statistics, optimization and information computing., 6 (3). pp. 398-408. ISSN 2311-004X. (Published) http://www.iapress.org/index.php/soic/article/view/soic.20180906/359 https://doi.org//10.19139/soic.v6i3.579 |
| spellingShingle | Q Science (General) QA Mathematics Noryanti, Muhammad Coolen-Maturi, Tahani Coolen, Frank PA Nonparametric predictive inference with parametric copulas for combining bivariate diagnostic tests |
| title | Nonparametric predictive inference with parametric copulas for combining bivariate diagnostic tests |
| title_full | Nonparametric predictive inference with parametric copulas for combining bivariate diagnostic tests |
| title_fullStr | Nonparametric predictive inference with parametric copulas for combining bivariate diagnostic tests |
| title_full_unstemmed | Nonparametric predictive inference with parametric copulas for combining bivariate diagnostic tests |
| title_short | Nonparametric predictive inference with parametric copulas for combining bivariate diagnostic tests |
| title_sort | nonparametric predictive inference with parametric copulas for combining bivariate diagnostic tests |
| topic | Q Science (General) QA Mathematics |
| url | http://umpir.ump.edu.my/id/eprint/22880/ http://umpir.ump.edu.my/id/eprint/22880/ http://umpir.ump.edu.my/id/eprint/22880/ http://umpir.ump.edu.my/id/eprint/22880/1/SOIC-FC-1708.pdf |