Highly Influenced

# Box – Cox transformations in linear models : large sample theory and tests of normality

@inproceedings{ChenBoxC, title={Box – Cox transformations in linear models : large sample theory and tests of normality}, author={Gemai Chen and Richard A. Lockhart and Michael A. Stephens} }

The authors provide a rigorous large sample theory for linear models whose endogenous variable has been subjected to the Box–Cox transformation. The theory provides a continuous asymptotic approximation to the distribution of natural estimates by focussing on the ratio of slope to standard deviation of the error term, since this parameter has a relatively stable and consistent estimate. The authors show the importance for inference of normality of the errors and give tests for normality based… CONTINUE READING