Premium
Bayesian analysis of the structural equation models with application to a longitudinal myopia trial
Author(s) -
Wang YiFu,
Fan TsaiHung
Publication year - 2011
Publication title -
statistics in medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.996
H-Index - 183
eISSN - 1097-0258
pISSN - 0277-6715
DOI - 10.1002/sim.4378
Subject(s) - structural equation modeling , bayesian probability , correlation , random effects model , optometry , econometrics , longitudinal data , bayesian inference , refractive error , markov chain monte carlo , statistics , mathematics , psychology , computer science , ophthalmology , medicine , eye disease , data mining , meta analysis , geometry
Myopia is becoming a significant public health problem, affecting more and more people. Studies indicate that there are two main factors, hereditary and environmental, suspected to have strong impact on myopia. Motivated by the increase in the number of people affected by this problem, this paper focuses primarily on the utilization of mathematical methods to gain further insight into their relationship with myopia. Accordingly, utilizing multidimensional longitudinal myopia data with correlation between both eyes, we develop a Bayesian structural equation model including random effects. With the aid of the MCMC method, it is capable of expressing the correlation between repeated measurements as well as the two‐eye correlation and can be used to explore the relational structure among the variables in the model. We consider four observed factors, including intraocular pressure, anterior chamber depth, lens thickness, and axial length. The results indicate that the genetic effect has much greater influence on myopia than the environmental effects. Copyright © 2011 John Wiley & Sons, Ltd.