Multilevel analyses in drug utilization research
(2024) p.169-179- Abstract
Multilevel regression analysis (MLRA) is a statistical technique that is suitable for the study of correlated outcomes within multilevel organisational and other data structures. This chapter provides a short introduction to MLRA, stressing the multilevel analysis of individual heterogeneity and discriminatory accuracy (MAIHDA) approach. It helps the readers to recognize the presence of multilevel structures in drug utilization research and assess when MAIHDA is necessary. From the statistical perspective, MLRA allows a better estimation of uncertainty by providing correct estimations of the standard errors of the regression coefficients in a regression analysis. Understanding unjustified medical practice variation is very relevant for... (More)
Multilevel regression analysis (MLRA) is a statistical technique that is suitable for the study of correlated outcomes within multilevel organisational and other data structures. This chapter provides a short introduction to MLRA, stressing the multilevel analysis of individual heterogeneity and discriminatory accuracy (MAIHDA) approach. It helps the readers to recognize the presence of multilevel structures in drug utilization research and assess when MAIHDA is necessary. From the statistical perspective, MLRA allows a better estimation of uncertainty by providing correct estimations of the standard errors of the regression coefficients in a regression analysis. Understanding unjustified medical practice variation is very relevant for the evaluation of healthcare quality since it can reflect inappropriate clinical decisions that can then be addressed. MAIHDA can also be applied when the higher-level units are cells in a matrix defined by combining several categorical variables.
(Less)
- author
- Merlo, Juan
LU
and Leckie, George LU
- organization
- publishing date
- 2024-01
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Drug utilization research, Healthcare quality, Maihda approach, Medical practice variation, Multilevel regression analysis
- host publication
- Drug Utilization Research : Methods and Applications: Second Edition - Methods and Applications: Second Edition
- pages
- 11 pages
- publisher
- Wiley
- external identifiers
-
- scopus:85211849013
- ISBN
- 9781119911685
- 9781119911654
- DOI
- 10.1002/9781119911685.ch16
- language
- English
- LU publication?
- yes
- id
- f2c3091a-f65e-4aa0-8a11-13516a95a26f
- date added to LUP
- 2025-01-27 12:05:53
- date last changed
- 2025-06-02 21:35:02
@inbook{f2c3091a-f65e-4aa0-8a11-13516a95a26f, abstract = {{<p>Multilevel regression analysis (MLRA) is a statistical technique that is suitable for the study of correlated outcomes within multilevel organisational and other data structures. This chapter provides a short introduction to MLRA, stressing the multilevel analysis of individual heterogeneity and discriminatory accuracy (MAIHDA) approach. It helps the readers to recognize the presence of multilevel structures in drug utilization research and assess when MAIHDA is necessary. From the statistical perspective, MLRA allows a better estimation of uncertainty by providing correct estimations of the standard errors of the regression coefficients in a regression analysis. Understanding unjustified medical practice variation is very relevant for the evaluation of healthcare quality since it can reflect inappropriate clinical decisions that can then be addressed. MAIHDA can also be applied when the higher-level units are cells in a matrix defined by combining several categorical variables.</p>}}, author = {{Merlo, Juan and Leckie, George}}, booktitle = {{Drug Utilization Research : Methods and Applications: Second Edition}}, isbn = {{9781119911685}}, keywords = {{Drug utilization research; Healthcare quality; Maihda approach; Medical practice variation; Multilevel regression analysis}}, language = {{eng}}, pages = {{169--179}}, publisher = {{Wiley}}, title = {{Multilevel analyses in drug utilization research}}, url = {{http://dx.doi.org/10.1002/9781119911685.ch16}}, doi = {{10.1002/9781119911685.ch16}}, year = {{2024}}, }