Log-transformation versus nonlinear regression in allometry

data analysis modeling strategy
1

The field of allometry has traditionally used log transformations for regressions. However, it has recently come into debate whether log transformations or nonlinear models are better suited. Please see the references below:

First, what are people’s thoughts on this? Personally, I think nonlinear models make more sense in this context, but I wanted to get other people’s opinions as well.

Second, Packard has proposed a strategy combining elements of ANOVA and nonlinear regression. Does anyone have particular thoughts on this approach?

2

I’d be interested to know if there are any disadvantages of ordinal regression in this context. Semiparametric ordinal regression is Y-transformation-free.

1 Like
3

I’m not sure. It would make sense, but I haven’t seen any literature on it