A Hybrid Model for Orthogonal Regression

Linear functional relationships are intended to be symmetric and therefore cannot generally accurately estimated using ordinary least squares regression equations. Orthogonal (OR) models allow for errors in both Y X can provide estimates of these relationships. The most well-established OR model, the errors-in-variables (EIV) assumes that observed scatter around line is due entirely measurement ratio error variances known. If variance known X, EIV model an unbiased maximum likelihood estimate a relationship. However, if substantial part variability natural variability, which not attributable or well defined directly applicable. main contribution this report development hybrid provides plausible linear cases with measurement. An analysis female male differential test functioning between essay objective used as parts licensure examination illustration use model.