Who belongs in the family?

By R. L. Thorndike. 1953

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

Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing (2021, methodology): “The elbow method (Thorndike, 1953), the silhouette method (Rousseeuw, 1987), or the Davies–Bouldin index (Davies & Bouldin, 1979), all could be used to determine the number of clusters since our method tends to produce well-separated values.”
An examination of indexes for determining the number of clusters in binary data sets (2002, background): “Therefore, besides looking at the maximum (or minimum) value maxk ik (where k is the number of clusters and ik the index value for k clusters) of the index, the following statistics are considered, see Thorndike, 1953; Kaufmann and Pape, 1996.”
Clustering trees: a visualization for evaluating clusterings at multiple resolutions (2018, background): “While there are methodsandstatistics(suchastheelbowmethod[7]andsilhou-ette plots [8]) designed to help analysts decide which clustering resolution to use, they typically produce a single score that only considers a single set of samples or clusters at a time.”
Uncovering novel mutational signatures by de novo extraction with SigProfilerExtractor (2020, unknown): “SigFit’s selection approach is based on the Elbow method.(30) SigProfilerExtractor leverages a modified version of the NMFk selection approach.”
General Growth Mixture Analysis with Antecedents and Consequences of Change (2010, unknown): “Analogous to the scree plot for principal component analysis, we could also plot the percent of total growth factor variance explained by the latent classes for each class enumeration, i.e., the ratio of the between-class growth factor variance for the total variance ( Thorndike 1953 ).”
A Cluster-Based Boosting Algorithm for Bankruptcy Prediction in a Highly Imbalanced Dataset (2018, methodology): “In this This method was proposed to ﬁnd the optimal ( k ) number of clusters in a speciﬁc dataset. experiment, the Elbow method [33], a famous method for determining Figure 4 shows the variation in distortion value for each value k over ﬁve repetitions and the average. five repetitions 4.2.”
A Review of Data-Driven Market Segmentation in Tourism (2002, background): “Although the roots of discussing this problem go back to Thorndike (1953), no satisfactory solution for this problem is available up to now.”
K-means clustering: a half-century synthesis. (2006, background): “Some authors (Gierl & Schwanenberg, 1998; Gower, 1975; Thorndike, 1953) advocate plotting the objective criterion (5) against varying values of K; a ‘flattening’ of the curve indicates the correct value of K.”
Deep learning improves antimicrobial peptide recognition (2018, methodology): “The setting of k ¼ 8 is selected after plotting the sum of squared distances between samples and cluster centroids for k ranging [1, 19] and looking for a bend based on the elbow method (Thorndike, 1953) (detailed analysis is shown in the Supplementary Information).”
Industry Induces Academic Science to Know Less about More1 (2010, background): “…criterion” enabled me to select the number of clusters that captured the most difference between terms in each dimension of the Arabidopsis corpus (Thorndike 1953; Goutte et al. 1999).24 Each term’s centrality within its cluster was measured with its internal Z-score, defined as , where is the…”