# (W Australia fish diets)

Re-open the workspace <ins>WA fish ws</ins> from C:\Examples v7\WA fish diets, which will provide an example where a 3-d MDS is necessary to get a reliable feel for the multivariate structure. The workspace <ins>WA fish ws</ins> should contain a data sheet <ins>Data2</ins> of the dietary assemblage of (pooled) guts of 7 marine fish species from W Australia, with uneven numbers of replicate pools per species. If not available, open <ins>WA fish diets %vol</ins>.pri; the <ins>Data2</ins> sheet simply excluded three samples, A9, B3, B4, which had much lower total gut content than the remaining 65 pools – see Section [3](https://learninghub.primer-e.com/books/primer-v7-user-manual-tutorial/chapter/3-highlighting-and-selection-select) on deselecting samples. Take **Pre-treatment>Standardise**>(Standardise•Samples) & (By•Total) and transform the result with Pre-treatment>Transform(overall)>(Transformation: <ins>Square root</ins>) and **Analyse>Resemblance**>(Measure•Bray-Curtis similarity), renaming this <ins>WA B-C sim</ins>.