Using machine-learning strategies to solve psychometric problems
Abstract Validating scales for clinical use is a common procedure in medicine and psychology. Through the application of computational methods, we present a new strategy for estimating construct validity and criterion validity. XGBoost, Random Forest and Support-Vector machine learning algorithms we...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-11-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-23678-9 |
| _version_ | 1798018186866589696 |
|---|---|
| author | Arthur Trognon Youssouf Ismail Cherifi Islem Habibi Loïs Demange Cécile Prudent |
| author_facet | Arthur Trognon Youssouf Ismail Cherifi Islem Habibi Loïs Demange Cécile Prudent |
| author_sort | Arthur Trognon |
| collection | DOAJ |
| description | Abstract Validating scales for clinical use is a common procedure in medicine and psychology. Through the application of computational methods, we present a new strategy for estimating construct validity and criterion validity. XGBoost, Random Forest and Support-Vector machine learning algorithms were employed in order to make predictions based on the pattern of participants’ responses by systematically controlling computational experiments with artificial experiments whose results are guaranteed. According to these findings, these approaches are capable of achieving construct and criterion validity and therefore could provide an additional layer of evidence to traditional validation approaches. In particular, this study examined the extent to which measured items are inferable by theoretically related items, as well as the extent to which the information carried by a given construct can be translated into other theoretically compatible normative scales based on other constructs (thereby providing information about construct validity); as well as the replicability of clinical decision rules on several partitions (thereby providing information about criterion validity). |
| first_indexed | 2024-04-11T16:19:51Z |
| format | Article |
| id | doaj.art-4ff56de1c2e44db3b5b81b0cb458f6cd |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-11T16:19:51Z |
| publishDate | 2022-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-4ff56de1c2e44db3b5b81b0cb458f6cd2022-12-22T04:14:24ZengNature PortfolioScientific Reports2045-23222022-11-011211910.1038/s41598-022-23678-9Using machine-learning strategies to solve psychometric problemsArthur Trognon0Youssouf Ismail Cherifi1Islem Habibi2Loïs Demange3Cécile Prudent4ClinicogINSERM, CNRS, Institut de la Vision, Sorbonne UniversitéClinicogLorraine UniversityBePsyLab, Angers UniversityAbstract Validating scales for clinical use is a common procedure in medicine and psychology. Through the application of computational methods, we present a new strategy for estimating construct validity and criterion validity. XGBoost, Random Forest and Support-Vector machine learning algorithms were employed in order to make predictions based on the pattern of participants’ responses by systematically controlling computational experiments with artificial experiments whose results are guaranteed. According to these findings, these approaches are capable of achieving construct and criterion validity and therefore could provide an additional layer of evidence to traditional validation approaches. In particular, this study examined the extent to which measured items are inferable by theoretically related items, as well as the extent to which the information carried by a given construct can be translated into other theoretically compatible normative scales based on other constructs (thereby providing information about construct validity); as well as the replicability of clinical decision rules on several partitions (thereby providing information about criterion validity).https://doi.org/10.1038/s41598-022-23678-9 |
| spellingShingle | Arthur Trognon Youssouf Ismail Cherifi Islem Habibi Loïs Demange Cécile Prudent Using machine-learning strategies to solve psychometric problems Scientific Reports |
| title | Using machine-learning strategies to solve psychometric problems |
| title_full | Using machine-learning strategies to solve psychometric problems |
| title_fullStr | Using machine-learning strategies to solve psychometric problems |
| title_full_unstemmed | Using machine-learning strategies to solve psychometric problems |
| title_short | Using machine-learning strategies to solve psychometric problems |
| title_sort | using machine learning strategies to solve psychometric problems |
| url | https://doi.org/10.1038/s41598-022-23678-9 |
| work_keys_str_mv | AT arthurtrognon usingmachinelearningstrategiestosolvepsychometricproblems AT youssoufismailcherifi usingmachinelearningstrategiestosolvepsychometricproblems AT islemhabibi usingmachinelearningstrategiestosolvepsychometricproblems AT loisdemange usingmachinelearningstrategiestosolvepsychometricproblems AT cecileprudent usingmachinelearningstrategiestosolvepsychometricproblems |