Symmetry Analysis of the Uncertain Alternative Box-Cox Regression Model

The asymmetry of residuals about the origin is a severe issue in estimating Box-Cox transformed model. In framework uncertainty theory, there are such theoretical issues regarding least-squares estimation (LSE) and maximum likelihood (MLE) linear models after transformation on response variables. Heretofore, only weighting methods for analysis have been available. This article proposes an uncertain alternative model to alleviate avoid λ tending negative infinity LSE or MLE. Such symmetry reasonable applications experts’ experimental data. parameter method was given via theorem, performance our supported numerical simulations. According simulations, proposed ‘alternative model’ can overcome problems grossly underestimated lambda residuals. estimated neither deviated from zero nor changed unevenly, clear contrast MLE downward biased Thus, though not applicable model, they fit Compared with systematically likely occur Both be used directly without constructing weighted method, offering better