Return to Answer

I'm assuming that a model which was fitted using the Error() function within aov() won't work when using in plot() because you will get more than one error stratum from which you can choose. Now according to this information here, one should use the proj() function which will give you the residuals for each error stratum, which then can be used for diagnostic plots.

I'm assuming that a model which was fitted using the Error() function within aov() won't work when using in plot() because you will get more than one error stratum from which you can choose. Now according to this information here, one should use the proj() function which will give you the residuals for each error stratum, which then can be used for diagnostic plots.

I'm assuming that a model which was fitted using the Error() function within aov() won't work when using in plot() because you will get more than one error stratum from which you can choose. Now you could use the proj() function which will give you the residuals for each error stratum in a way that allows you to extract them more easily. I found some information here.

I'm assuming that a model which was fitted using the Error() function within aov() won't work when using in plot() because you will get more than one error stratum from which you can choose. Now according to this information here, one should use the proj() function which will give you the residuals for each error stratum, which then can be used for diagnostic plots.

Thus fitted(oats.aov[[4]]) and resid(oats.aov[[4]]) are vectors of length 54 representing fitted values and residuals from the last stratum, based on 54 orthonormal linear functions of the original data vector. It is not possible to associate them uniquely with the plots of the original experiment.

Thus fitted(oats.aov[[4]]) and resid(oats.aov[[4]]) are vectors of length 54 representing fitted values and residuals from the last stratum, based on 54 orthonormal linear functions of the original data vector. It is not possible to associate them uniquely with the plots of the original experiment. The function proj takes a fitted model object and finds the projections of the original data vector onto the subspaces defined by each line in the analysis of variance tables (including, for multistratum objects, the suppressed table with the grand mean only). The result is a list of matrices, one for each stratum, where the column names for each are the component names from the analysis of variance tables.