Citation, DOI, disclosures and article data
At the time the article was created Candace Makeda Moore had no recorded disclosures.View Candace Makeda Moore's current disclosures
At the time the article was last revised Andrew Murphy had no recorded disclosures.View Andrew Murphy's current disclosures
Multivariate ANOVA (MANOVA) are statistical tests which compare multiple groups in terms of more than one dependent variable. The MANOVA is similar to the simpler ANOVA but examines the means of multiple dependant variables. Like the ANOVA, certain assumptions about the data must be true for the test to be unarguably valid. MANOVA tests are highly useful in all of medicine as we are often want to create a study with more than two arms, or look at a population with several possible charecteristics and understand the results or differences in terms of more than one outcome. In radiology specifically the test is sometimes used to examine how reproducible certain measurements are between different modalities and/or in terms of humans versus automated computation 1,2. In some cases the results of a MANOVA will differ from a bunch of ANOVA tests performed on the individual dependant variables, and this is often because the MANOVA is more powerful 3.
- 1. Caballo M, Pangallo DR, Mann RM, Sechopoulos I. Deep learning-based segmentation of breast masses in dedicated breast CT imaging: Radiomic feature stability between radiologists and artificial intelligence. (2020) Computers in biology and medicine. 118: 103629. doi:10.1016/j.compbiomed.2020.103629 - Pubmed
- 2. V Kumar, JB Ludlow, A Mol, L Cevidanes. Comparison of conventional and cone beam CT synthesized cephalograms. (2014) Dentomaxillofacial Radiology. 36 (5): 263-9. doi:10.1259/dmfr/98032356 - Pubmed
- 3. Rudy, T. E., Kubinski, J. A., & Boston, J. R. (1992). Multivariate analysis and repeated measurements: A primer. Journal of Critical Care, 7(1), 30–41. doi:10.1016/0883-9441(92)90006-s