`dist_sc_group.Rd`

The `dist_sc_group`

function computes a distance matrix for each group of
scoring criteria and then averages the pair-wise distances across groups.
This allows the computation of a more weighted distance measure and a
closer clustering of indicators that e.g. respond to the same pressure types.

dist_sc_group(x, method_dist = "euclidean", ...)

x | A list of data frames or matrices that contain the indicator scores
per group (see details). This could be the |
---|---|

method_dist | Dissimilarity index used in the |

... | Further arguments to be passed to the method |

The function returns a `dist`

object.

Ordinary distance measures such as the Euclidean, Bray Curtis or Canberra distance treat all variables, i.e. here the criteria, the same, which might be not always desirable. For instance, two indicators that show no trend but respond each to a specific type of fishing pressure (with a score of 1) and a third indicator that only shows a trend (score of 1 here) would have all the same distance to each other. So to add more weight to the similarity of the first two indicators responding to the same pressure type, this function computes separate distance matrices that are then averaged.

`summary_sc`

and `vegdist`

for the
computation of the dissimilarity index

Other score-based IND performance functions:
`clust_sc()`

,
`dist_sc()`

,
`expect_resp()`

,
`plot_clust_sc()`

,
`plot_spiechart()`

,
`scoring()`

,
`summary_sc()`

# Using the Baltic Sea demo data scores_tbl <- scoring(trend_tbl = model_trend_ex, mod_tbl = all_results_ex, press_type = press_type_ex) scores_mat <- summary_sc(scores_tbl)$scores_matrix # Split the scores by pressure-independent criteria and pressure types dist_matrix <- dist_sc_group(x = list( scores_mat[,1:2], scores_mat[,3:8], scores_mat[,9:12], scores_mat[,13:16]) )