No, MANOVA requires multiple continuous outcomes.

Mehmet Sinan Iyisoy

Thank you for the answer, what do you suggest?

Thanks again

J

Hi Jamal Wadi MD,

In your application context, some variants of MANOVA may be usefull when addressing discrete outputs :

• Cai et al., "High-dimensional sparse MANOVA", 2014 ( https://www.google.fr/url?sa=t&rct=j&q=&esrc=s&source=web&cd=2&cad=rja&uact=8&ved=0ahUKEwin5uaGmZfUAhXHBBoKHeYFDmQQFgg7MAE&url=http%3A%2F%2Fwww-stat.wharton.upenn.edu%2F~tcai%2Fpaper%2FSparse-MANOVA.pdf&usg=AFQjCNFymwR6D_0r0GYqSLhll1xLRVtR3A )
• Engel et al., "Regularized MANOVA (rMANOVA) in Untargeted Metabolomics", 2015 ( http://booksc.org/dl/44671962/1e8f66 )
• Smilde et al., "ANOVA-simultaneous component analysis (ASCA): a new tool for analyzing designed metabolomics data", 2005 ( http://booksc.org/dl/31215047/714000 )

If the ordering of the outputs is mandatory, it is more convenient to check for multivariate ordinal regression methods:

• Doyle et al., "Multivariate decoding of brain images using ordinal regression", 2013 ( https://www.researchgate.net/profile/Steven_Williams3/publication/236919294_Multivariate_decoding_of_brain_images_using_ordinal_regression/links/567bd0f508ae19758381ab62.pdf ),
• Pedregosa et al., "On the Consistency of Ordinal Regression Methods", 2015 ( https://hal.inria.fr/hal-01054942v3/document )

Finally, discrete CCA (Canonical Correlation Analysis) may also be usefull:

• Podosinnikova et al., "Beyond CCA: Moment Matching for Multi-View Models", 2016 ( https://arxiv.org/pdf/1602.09013v1.pdf )

Hoping it will be helpfull

Article Multivariate decoding of brain images using ordinal regression

Dear Hi Jamal Wadi MD,

This paper by Rouder et al., "Default Bayes Factors for ANOVA Designs", 2012 covers your need fairly well:

http://pcl.missouri.edu/sites/default/files/Rouder.JMP_.2012.pdf

Best Regards

Stéphane Breton

THANK YOU SO MUCH