Original Research

Application of multivariate analysis of vari-ance (MANOVA) to distance refractive vari-ability and mean distance refractive state

S Abelman
African Vision and Eye Health | South African Optometrist: Vol 65, No 2 | a259 | DOI: https://doi.org/10.4102/aveh.v65i2.259 | © 2006 S Abelman | This work is licensed under CC Attribution 4.0
Submitted: 19 December 2006 | Published: 19 December 2006

About the author(s)

S Abelman, Centre for Numerical Analysis and Computational Mathematics, School of Computational and Ap-plied Mathematics, University of the Witwatersrand, Private Bag 3, Wits 2050, South Africa

Full Text:

PDF (325KB)


Refractive state can be regarded as a dynam-ic quantity. Multiple measurements of refractive state can be determined easily and rapidly on a number of different occasions using an autore-fractor. In an experimental trial undertaken by Gillan, a 30-year-old female was subjected to 30 autorefractor measurements each taken at vari-ous intervals before and after the instillation of Mydriacyl 1% (tropicamide) into her right eye. The purpose of this paper is to apply multivar-iate analysis of variance (MANOVA) to Gillan’s sample data in order to assess whether instillation of Mydriacyl into the eye affects variability of distance refractive state as well as mean distance refractive state as measured by an autorefractor. In  five  of  the  seven  cases  where  pairwise hypotheses  tests  were  performed,  it  is  con-cluded that at a 99% level of confidence there is no difference in variability of distance refrac-tive state before and after cycloplegia. In two of the three cases where MANOVA was applied, there is a significant difference at a 95% and at a 99% level of confidence in both variability of distance refractive state and mean distance refractive  state  with  and  without  cycloplegia.


Multivariate analysis of variance (MANOVA), hypothesis testing


Total abstract views: 3309
Total article views: 3526

Crossref Citations

No related citations found.