Table 1.

Description of selected methods with regards to design questions related to (1) similarities/distances or data transformation, (2) methodology to merge numerical and categorical parts and (3) algorithm choice.

Clustering method	Q1: Distance or transformation		Q2: Merge mode	Q3: Optimization algorithm
	Numeric	Categorical
Distance-based methods
PAMa	Normalized difference	Hamming	Gowerb	K-medoids
	UETc	UETc	NA	K-medoids
Ascendant hierarchical clusteringd	Normalized difference	Hamming	Gowerb	HAC + Ward link
	UETc	UETc	NA	HAC + ward link
Kprotoe	Euclidean	Hamming	Weighted sum	Kmeans
Model-based methods
Kamilaf	Euclidean	Probabilities	ensemble-like approach	K-means and EM
LCAg	Discretisation and probabilities	Probabilities	NA	EM and Newton–Raphson
LCMh	Probabilities	Probabilities	NA	EM + feature selection
Mixmodi	Probabilities	Probabilities	NA	EM

NA, Not applicable; EM, Expectation Maximization ; PAM, Partitioning Around Medoids; HAC, Hierarchical Ascendant Clustering; UET, Unsupervised Extra Trees dissimilarity.

^aclustMixType package (PAM function): https://cran.r-project.org/web/packages/clustMixType.

^bCluster package (daisy function): https://cran.r-project.org/web/packages/cluster.

^cYet unpublished UET package, available at https://gitlab.inria.fr/kdalleau/uetcpp, build_randomized_tree_and_get_sim function.

^dStats (R-base package, hclust function): https://stat.ethz.ch/R-manual//R-devel/library/stats/html/00Index.html.

^eclustMixType package (kproto function); see ^a.

^fKamila package (kamila function): https://cran.r-project.org/web/packages/kamila.

^gpoLCA package (poLCA function): https://cran.r-project.org/web/packages/poLCA.

^hVarSelLCM package (VarSelCluster function): https://cran.r-project.org/web/packages/VarSelLCM.

ⁱRmixmod package (mixmodCluster function): https://cran.r-project.org/web/packages/Rmixmod.