Dear list, does anyone know if it is possible to fit a RMA (Reduced Major Axis, or model II) regression in limma? The difference should basically be that it assumes error on the x as well, instead of just on the response variable. In other words, instead of minimizing the the residual on the vertical axis, it tries to minimize the area between x- and y- residuals. It would be extremely helpful for me, because the line of best fit doesn't change when Y~X or X~Y. I would need an estimate for the slope of the line when I swap the variables, but with a normal regression I guess I can't just do 1/b. Thanks, paolo -- Paolo Innocenti Department of Animal Ecology, EBC Uppsala University Norbyv?gen 18D 75236 Uppsala, Sweden