The proof and measurement of association between two things. By C. Spearman, 1904.
By C. Spearman. 1987
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
- Are Labels Necessary for Neural Architecture Search? (2020, methodology): “For the rank correlation analysis, we empirically study the statistical rank correlations between the pretext task accuracy and the supervised accuracy, by measuring the Spearman’s Rank Correlation [28], denoted as ρ.”
- Bayesian Neural Word Embedding (2016, methodology): “In order to compare between the BSG and SG methods, we compute for each method the Spearman [17] rank correlation coefficient with respect to the ground truth.”
- Off-Policy Evaluation via Off-Policy Classification (2019, methodology): “We report two correlations, the coefficient of determination R of line of best fit, and the Spearman rank correlation ξ [33].”
- SimGNN: A Neural Network Approach to Fast Graph Similarity Computation (2018, unknown): “verage squared difference between the computed similarities and the ground-truth similarities. We also adopt the following metrics to evaluate the ranking results. Spearman’sRankCorrelationCoefficient(ρ)[46]andKendall’s Rank Correlation Coefficient (τ) [24] measure how well the predicted ranking results ”
- A Correlation between Inclination and Color in the Classical Kuiper Belt (2002, methodology): “The KBO Inclination and Color Correlation To estimate the significance of the relationship between color and i, we computed the Spearman (1904) rank correlation statistic r for our data set, which takes on non-zero values between −1 r 1 for correlated quantities.”
- Preference-based interactive multi-document summarisation (2019, methodology): “For each cluster x, we measure the quality of Ûx by its Spearman’s rank correlation (Spearman 1904) to the gold-standard utility scores U∗ x (Eq. (12)) over all summaries in DS(x). We normalise Ûx to the same range of U ∗ x (i.e. [0,10]). For the vector representation φ, we use the same 200-dimensio”
- The reliability paradox: Why robust cognitive tasks do not produce reliable individual differences (2017, background): “This meaning of reliability is a fundamental consideration for individual differences research because the reliability of two measures limits the correlation that can be observed between them (Nunnally, 1970; Spearman, 1904).”
- Using WordNet-based Context Vectors to Estimate the Semantic Relatedness of Concepts (2006, methodology): “(Spearman, 1904) is used to assess the equivalence of two rankings.”
- Well-Read Students Learn Better: On the Importance of Pre-training Compact Models (2019, methodology): “is more robust to mismatches between D Land D T. We measure domain shift using the Spearman rank correlation coefficient (which we refer to as Spearman or simply S), introduced as a general metric in (Spearman, 1904) and first used as a corpus similarity metric in (Johansson et al., 1989). To compute ”
- THE PdBI ARCSECOND WHIRLPOOL SURVEY (PAWS): ENVIRONMENTAL DEPENDENCE OF GIANT MOLECULAR CLOUD PROPERTIES IN M51 (2014, methodology): “To estimate the degree of correlation between GMC properties we calculate the Spearman’s rank correlation coefficient (Spearman 1904).”
- At what sample size do latent variable correlations stabilize? (2018, methodology): “, Cronbach’s coefficient alpha; or McDonald’s coefficient omega) of the composite scores (Nunnally & Bernstein, 1994; Spearman, 1904).”
- Homogeneous studies of transiting extrasolar planets - III. Additional planets and stellar models (2010, background): “…(which may be a fundamentally different population to the lower mass ones; Fabrycky & Winn 2009; Southworth et al. 2009c), the rank correlation test of Spearman (1904) returns a probability of 99.80% (3.1σ) that thePorb–gb correlation is real and 97.6% (2.3σ) that thePorb–Mb correlation is real.”