Table 2.

Breakdown of methods used by studies applying hierarchical clustering with Ward's linkage (N=23).

Data type, dissimilarity, and scaling of continuous features			Categorical features encoded as binary?	Value, n (%)
Continuous
	Euclidean assumed
		Not detailed	N/Aa	1 (4)
Mixed
	Euclidean assumed
		Scaled but method unspecified	Yes No	1 (4) 1 (4)
		Scaled to lie in the interval of 0 to 1	Yes	1 (4)
		z-scores	Yes No	1 (4) 1 (4)
		Not detailed	Yes No	3 (13) 6 (26)
	Euclidean stated
		z-scores	Yes No	2 (9) 1 (4)
	Gowerb
		Gower standardisation	No	3 (13)
		Scaled but method unspecified	No	1 (4)
	treeClust
		Not detailed	No	1 (4)

^aN/A: not applicable (irrelevant for continuous features).

^bComputing the Gower coefficient normalizes the distance between feature samples by dividing by the feature range. Therefore, it is not necessary to normalize continuous features prior to computing the Gower coefficient.