Gavin Simpson

@heronoh No updates; I guess this stalled when I realised that they way `envfit` is implemented, it wouldn't have lead to much improvement (I assumed) because the parallelisation I had...

@jarioksa Yeah; after initially misunderstanding how `mcapply` works (as I was following `permutest.cca` too closely; that code actually ends up iterating over perms in C AFAICT), I have `vectorfit()` working...

All of this would be clearer if people use `dbrda()` instead of `adonis2()` - then we could use `Condition()` and think about doing a design-based or model-based permutation test directly...

You could extract the scores you want to plot and add jitter to them using `jitter()` and then plot them, to stay within the base graphics paradigm. If you want...

These things are showing slightly different things, and the details can be important. Using the following as an example to illustrate ```r data(varespec) ## Bray-Curtis distances between samples dis with(mod,...

@ClaireG26 Could you please clarify your question? At present it mentions `Zone`, `Site` and `Treatment`, a formula in the code/model that contains **none** of these and data that has an...

Also @ClaireG26 please run your code - there is no way your example will run even if you fix the description as the data for the species are characters. You...

@ClaireG26 Right now, it looks like you have two sites. Within each site you have 4 plots. Two plots are on zone `h` and two are on `l`. Within each...

I don't think differently; I consider these at best a guide to the potential/likely dimensionality, not some infallible, all-knowing method that can discern the will of . Bootstrapping eigenvalues seems...

I would add that the more formal approaches to doing unconstrained ordination, such as using latent variable models, would allow a real statistical (as opposed to an heuristical) solution to...