A General Coefficient of Similarity and Some of Its Properties

By John C. Gower. 1971

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

FairSight: Visual Analytics for Fairness in Decision Making (2019, methodology): “For Input space, we calculate the Gower distance dI(·) [16] between Xi and Xj , which measures the pairwise distance of the two individuals’ feature representations.”
Benchmark and Survey of Automated Machine Learning Frameworks (2019, methodology): “To account for the mixed-type vector representations, the Gower distance (Gower, 1971) is used as the distance metric between two configurations.”
SPSS TwoStep Cluster - a first evaluation (2004, methodology): “If the variables have different measurement levels, either a general distance measure (like Gower's general similarity measure; Gower 1971) may be used or the nominal (and ordinal) variables may be transformed to dummies and treated as quantitative 5 (Bender et al. 2001; Wishart 2003).”
Assessing the suitability of diversity metrics to detect biodiversity change (2017, methodology): “For this, for each communitywe randomly sampled one ormore biological traits (body mass, diet, and affinity for the two habitats), and used them to generate a distance matrix based on Gower's distance, as it allows using both continuous and categorical data types (Gower, 1971).”
Local environment and space drive multiple facets of stream macroinvertebrate beta diversity (2018, methodology): “Before acquiring these matrices, we used the Gower distance (Gower, 1971) to calculate between‐species distances based on the trait data using the function gowdis in the R package FD (Laliberté, Legendre, & Shipley, 2014).”
Multi-Objective Counterfactual Explanations (2020, methodology): “The second component o2 quantifies the distance between x ∗ and x using the Gower distance to account for mixed features [10]: o2(x,x ∗) = 1 p p ∑ j=1 δG(xj , x ∗ j ) ∈ [0, 1] with p being the number of features.”
The Impact of Regulatory Heterogeneity on Agri‐Food Trade (2012, unknown): “The index is developed according to the Gower index of (dis)similarity (Gower, 1971).”
ANN-DT: an algorithm for extraction of decision trees from artificial neural networks (1999, methodology): “For discrete data other measures of similarity can be defined [29], while the Euclidean distance or a metric defined by Gower [ 30 ] can also be used for mixed data.”
Predictive soil mapping with limited sample data (2015, background): “Certainly other similarity/distance measurements defined in the environmental feature space, such as taxonomic distance (Minasny & McBratney, 2007), Gower similarity coefficient (Gower, 1971), Euclidian distance or Manhattan distance, can also be used.”
Response of forest plant species to land‐use change: a life‐history trait‐based approach (2003, methodology): “This was done by calculating Gower’s Similarity Coefficients (GSC; Gower 1971) among a subset of species for which information was available on more than 50% of the studied traits (102 and 44 European and American herbs and 25 European graminoids).”
A sampling strategy for conserving genetic diversity when forming core subsets (2005, methodology): “In Method (MLM) strategy in which the Gower (1971) these allocation methods, the number of accessions sampled per clus- distance is used as a measure of similarity (or distance) ter is proportional to (i) the mean of the Gower’s distance between among accessions considering all continuous and…”
Specialist species of wood‐inhabiting fungi struggle while generalists thrive in fragmented boreal forests (2013, methodology): “…between the patterns of species occurrences (R1–R7 and S1–S5) by a twodimensional non-metric multidimensional scaling (NMDS; Venables & Ripley 2002; Oksanen et al. 2012) in which we located the species according to the pairwise dissimilarities (Gower 1971) of the variables R1–R7 and S1–S5.”
From Classical to Canonical Ordination (2012, methodology): “2) For physical or chemical data, an alternative to the Euclidean distance is to compute the Gower (1971) coefficient of similarity, followed by a transformation of the similarities to distances.”
Long-Period Cycles of the Sun's Activity Recorded in Direct Solar Data and Proxies (2002, background): “…more popular measures of similarity of cases i and j , having features k = 1, 2, . . . , is the general similarity coefficient gij , suggested by Gower (1971): gij = p∑ k=1 Ui jk p∑ k=1 Wijk , (7) where Uijk denotes the contribution provided by the kth variable, Wijk− are information weight…”
A Taxonomic Revision of Echinacea (Asteraceae: Heliantheae) (2009, methodology): “Gower’s coefficient of similarity (Gower 1971), which accounts for missing values and combines weighted or unweighted, binary, alternative, qualitative, quantitative, and semi-quantitative characters (St-Laurent et al. 2000), was computed for each pair of individuals in the original matrix, giving…”