scholarly journals A comparison of 71 binary similarity coefficients: The effect of base rates

PLoS ONE ◽  
2021 ◽  
Vol 16 (4) ◽  
pp. e0247751
Author(s):  
Michael Brusco ◽  
J. Dennis Cradit ◽  
Douglas Steinley

There are many psychological applications that require collapsing the information in a two-mode (e.g., respondents-by-attributes) binary matrix into a one-mode (e.g., attributes-by-attributes) similarity matrix. This process requires the selection of a measure of similarity between binary attributes. A vast number of binary similarity coefficients have been proposed in fields such as biology, geology, and ecology. Although previous studies have reported cluster analyses of binary similarity coefficients, there has been little exploration of how cluster memberships are affected by the base rates (percentage of ones) for the binary attributes. We conducted a simulation experiment that compared two-cluster K-median partitions of 71 binary similarity coefficients based on their pairwise correlations obtained under 15 different base-rate configurations. The results reveal that some subsets of coefficients consistently group together regardless of the base rates. However, there are other subsets of coefficients that group together for some base rates, but not for others.

2013 ◽  
Vol 734-737 ◽  
pp. 3071-3074
Author(s):  
Guo Dong Zhang ◽  
Zhong Liu

Aiming at the phenomenon that the chaff and corner reflector released by surface ship can influence the selection of missile seeker, this paper proposed a multi-target selection method based on the prior information of false targets distribution and Support Vector Machine (SVM). By analyzing the false targets distribution law we obtain two classification principles, which are used to train the SVM studies the true and false target characteristics. The trained SVM is applied to the seeker in the target selection. This method has advantages of simple programming and high classification accuracy, and the simulation experiment in this paper confirms the correctness and effectiveness of this method.


2010 ◽  
Vol 13 (05) ◽  
pp. 607-619 ◽  
Author(s):  
DIEMO URBIG

Previous research investigating base rate neglect as a bias in human information processing has focused on isolated individuals. This study complements this research by showing that in settings of interacting individuals, especially in settings of social learning, where individuals can learn from one another, base rate neglect can increase a population's welfare. This study further supports the research arguing that a population with members biased by neglecting base rates does not need to perform worse than a population with unbiased members. Adapting the model of social learning suggested by Bikhchandani, Hirshleifer and Welch (The Journal of Political Economy100 (1992) 992–1026) and including base rates that differ from generic cases such as 50–50, conditions are identified that make underweighting base rate information increasing the population's welfare. The base rate neglect can start a social learning process that otherwise had not been started and thus base rate neglect can generate positive externalities improving a population's welfare.


2019 ◽  
Vol 4 (1) ◽  
pp. 64-67
Author(s):  
Pavel Kim

One of the fundamental tasks of cluster analysis is the partitioning of multidimensional data samples into groups of clusters – objects, which are closed in the sense of some given measure of similarity. In a some of problems, the number of clusters is set a priori, but more often it is required to determine them in the course of solving clustering. With a large number of clusters, especially if the data is “noisy,” the task becomes difficult for analyzing by experts, so it is artificially reduces the number of consideration clusters. The formal means of merging the “neighboring” clusters are considered, creating the basis for parameterizing the number of significant clusters in the “natural” clustering model [1].


2016 ◽  
Vol 113 (27) ◽  
pp. 7475-7480 ◽  
Author(s):  
Jack Cao ◽  
Mahzarin R. Banaji

Meet Jonathan and Elizabeth. One person is a doctor and the other is a nurse. Who is the doctor? When nothing else is known, the base rate principle favors Jonathan to be the doctor and the fairness principle favors both individuals equally. However, when individuating facts reveal who is actually the doctor, base rates and fairness become irrelevant, as the facts make the correct answer clear. In three experiments, explicit and implicit beliefs were measured before and after individuating facts were learned. These facts were either stereotypic (e.g., Jonathan is the doctor, Elizabeth is the nurse) or counterstereotypic (e.g., Elizabeth is the doctor, Jonathan is the nurse). Results showed that before individuating facts were learned, explicit beliefs followed the fairness principle, whereas implicit beliefs followed the base rate principle. After individuating facts were learned, explicit beliefs correctly aligned with stereotypic and counterstereotypic facts. Implicit beliefs, however, were immune to counterstereotypic facts and continued to follow the base rate principle. Having established the robustness and generality of these results, a fourth experiment verified that gender stereotypes played a causal role: when both individuals were male, explicit and implicit beliefs alike correctly converged with individuating facts. Taken together, these experiments demonstrate that explicit beliefs uphold fairness and incorporate obvious and relevant facts, but implicit beliefs uphold base rates and appear relatively impervious to counterstereotypic facts.


1999 ◽  
Vol 5 (1) ◽  
pp. 26-31 ◽  
Author(s):  
JACQUES DONDERS

The standardization data for the California Verbal Learning Test–Children's Version (CVLT–C) were used to evaluate statistically significant discrepancies between key quantitative variables of this instrument, as well as the base rate of specific discrepancies. The results indicated that apparently large discrepancies between the respective standard scores were actually fairly common. However, for 3 of the 4 contrasts, discrepancies that equaled or exceeded 1.5 z-score points in the hypothesized direction were sufficiently unusual to be considered clinically significant. For a 4th contrast, discrepancies that equaled or exceeded 1 z-score point in the hypothesized direction appeared to meet this criterion. It is suggested that the interpretation of clinically obtained CVLT–C profiles should focus primarily on specific quantitative variables, with inclusion of consideration of the presented base rates of discrepancies between the respective z scores. (JINS, 1999, 5, 26–31.)


2001 ◽  
Vol 7 (7) ◽  
pp. 875-880 ◽  
Author(s):  
KEITH A. HAWKINS ◽  
DAVID S. TULSKY

Since memory performance expectations may be IQ-based, unidirectional base rate data for IQ-Memory Score discrepancies are provided in the WAIS–III/WMS–III Technical Manual. The utility of these data partially rests on the assumption that discrepancy base rates do not vary across ability levels. FSIQ stratified base rate data generated from the standardization sample, however, demonstrate substantial variability across the IQ spectrum. A superiority of memory score over FSIQ is typical at lower IQ levels, whereas the converse is true at higher IQ levels. These data indicate that the use of IQ–memory score unstratified “simple difference” tables could lead to erroneous conclusions for clients with low or high IQ. IQ stratified standardization base rate data are provided as a complement to the “predicted difference” method detailed in the Technical Manual. (JINS, 2001, 7, 875–880.)


2008 ◽  
Vol 90 (1) ◽  
pp. 23-32 ◽  
Author(s):  
Florian Kutzner ◽  
Peter Freytag ◽  
Tobias Vogel ◽  
Klaus Fiedler

1991 ◽  
Vol 4 ◽  
pp. 123-135
Author(s):  
Philip W. Signor

The fossil record is replete with patterns. Nearly two centuries of intensive paleontological research has produced a vast number of apparent patterns: stratigraphic and temporal distributions of taxa, paleogeographic distributions, paleoecological relationships, patterns of co-occurrence, morphology and morphological variation, and so forth. Many of these patterns reflect the interplay of important intrinsic processes operating within the biosphere and extrinsic influences acting from without. Others, however, follow from the ordinary processes of everyday life and require no special explanation. How, then, are inquiring paleontologists to separate meaningful patterns from the meaningless? For the most part, the selection of patterns appropriate for further study and explication has remained a matter of subjective judgment.


Water ◽  
2019 ◽  
Vol 11 (4) ◽  
pp. 812 ◽  
Author(s):  
Pengfei Shi ◽  
Tao Yang ◽  
Bin Yong ◽  
Zhenya Li ◽  
Chong-Yu Xu ◽  
...  

The absence of aggregated uncertainty measures restricts the assessment of uncertainty in hydrological simulation. In this work, a new composite uncertainty measure is developed to evaluate the complex behaviors of uncertainty existing in hydrological simulation. The composite uncertainty measure is constructed based on a framework, which includes three steps: (1) identification of behavioral measures by analyzing the pairwise correlations among different measures and removing high correlations; (2) weight assignment by means of a new hierarchical weight assembly (HWA) approach incorporating the intra-class and inter-class weights; (3) construction of a composite uncertainty measure through incorporating multiple properties of the measure matrix. The framework and the composite uncertainty measure are demonstrated by case studies in uncertainty assessment for hydrological simulation. Results indicate that the framework is efficient to generate a composite uncertainty index (denoted as CUI) and the new measure CUI is competent for uncertainty evaluation. Besides, the HWA approach performs well in weighting, which can characterize subjective and objective properties of the information matrix. The achievement of this work provides promising insights into the performance comparison of uncertainty analysis approaches, the selection of proper cut-off threshold in the GLUE method, and the guidance of reasonable uncertainty assessment in a range of environmental modelling.


2019 ◽  
Vol 38 (5) ◽  
pp. 539-550
Author(s):  
Ash Puttaswamy ◽  
Anjelica Barone ◽  
Kathleen D. Viezel ◽  
John O. Willis ◽  
Ron Dumont

An area of particular importance when examining index scores on the Wechsler Intelligence Scale for Children–Fifth Edition (WISC-V) is the utilization and interpretation of critical values and base rates associated with differences between an individual’s subtest scaled score and the individual’s mean scaled score for an index. For the WISC-V, critical value and base rate information is provided for the core subtests contained within each of the primary indices. However, critical value and base rate information is not provided by the test publisher for subtests within the Quantitative Reasoning Index (QRI), Auditory Working Memory Index (AWMI), Nonverbal Index (NVI), General Ability Index (GAI), Cognitive Proficiency Index (CPI), Naming Speed Index (NSI), Symbol Translation Index (STI), and Storage and Retrieval Index (SRI). This study investigates and provides critical values and base rates for performance on the QRI, AWMI, NVI, GAI, CPI, NSI, STI, and SRI.


Sign in / Sign up

Export Citation Format

Share Document