The Experts below are selected from a list of 2673 Experts worldwide ranked by ideXlab platform

Gonçalo Ferraz - One of the best experts on this subject based on the ideXlab platform.

  • Is hearing believing? Patterns of bird voice misidentification in an online quiz
    Revista Brasileira de Ornitologia, 2016
    Co-Authors: Bento Collares Gonçalves, Gonçalo Ferraz
    Abstract:

    This study aims to uncover patterns of species identification error in bioacoustic surveys of central Amazon birds. To quantify errors, we developed an on-line quiz based on vocalizations of an undisclosed set of 41 antbird (Thamnophilidae) and woodcreeper (Dendrocolaptinae) species. We invited experts to answer the quiz and obtained 820 answers from 20 participants. The answers were compared to the results of a Binomial Experiment with a success probability of 0.5; i.e. we examined whether participants identified species correctly more often than expected by the toss of a coin with a 50% chance of producing the right identification. We also examined whether species were correctly identified more often than expected under a similar coin toss Experiment. Quiz answers were compiled in a triangular matrix showing species ranked by taxonomic order on both axes. From the triangular matrix we can ask whether closely-related species were mistaken for each other, i.e. confused, more often than distantly- related species. We tested this hypothesis with a null model approach that compared the mean taxonomic distance between confused species in the observed matrix to the distribution of mean taxonomic distances between confused species in 10,000 randomized matrices. Finally, we drew a dendrogram to represent the similarity between species with regard to the distribution of identification errors. The 20 participants who took the quiz showed substantial variation in their ability to identify species correctly. Fourteen species were correctly identified more often than expected at random, while only one was misidentified more often than expected at random. The observed mean distance between confused species was smaller than all of the mean distances from the randomized, null-model matrices, indicating that confusions are more frequent between closely related species than between distant ones.

  • Is hearing believing? Patterns of bird voice misidentification in an online quiz
    Revista Brasileira de Ornitologia, 2016
    Co-Authors: Bento Collares Gonçalves, Gonçalo Ferraz
    Abstract:

    This study aims to uncover patterns of species identification error in bioacoustic surveys of central Amazon birds. To quantify errors, we developed an on-line quiz based on vocalizations of an undisclosed set of 41 antbird (Thamnophilidae) and woodcreeper (Dendrocolaptinae) species. We invited experts to answer the quiz and obtained 820 answers from 20 participants. The answers were compared to the results of a Binomial Experiment with a success probability of 0.5; i.e. we examined whether participants identified species correctly more often than expected by the toss of a coin with a 50% chance of producing the right identification. We also examined whether species were correctly identified more often than expected under a similar coin toss Experiment. Quiz answers were compiled in a triangular matrix showing species ranked by taxonomic order on both axes. From the triangular matrix we can ask whether closely-related species were mistaken for each other, i.e. confused, more often than distantly-related species. We tested this hypothesis with a null model approach that compared the mean taxonomic distance between confused species in the observed matrix to the distribution of mean taxonomie distances between confused species in 10,000 randomized matrices. Finally, we drew a dendrogram to represent the similarity between species with regard to the distribution of identification errors. The 20 participants who took the quiz showed substantial variation in their ability to identify species correctly. Fourteen species were correctly identified more often than expected at random, while only one was misidentified more often than expected at random. The observed mean distance between confused species was smaller than all of the mean distances from the randomized, null-model matrices, indicating that confusions are more frequent between closely related species than between distant ones.

V Rajeswaran - One of the best experts on this subject based on the ideXlab platform.

  • proportion a comprehensive r package for inference on single Binomial proportion and bayesian computations
    SoftwareX, 2017
    Co-Authors: Maheswari Subbiah, V Rajeswaran
    Abstract:

    Abstract Extensive statistical practice has shown the importance and relevance of the inferential problem of estimating probability parameters in a Binomial Experiment; especially on the issues of competing intervals from frequentist, Bayesian, and Bootstrap approaches. The package written in the free R environment and presented in this paper tries to take care of the issues just highlighted, by pooling a number of widely available and well-performing methods and apporting on them essential variations. A wide range of functions helps users with differing skills to estimate, evaluate, summarize, numerically and graphically, various measures adopting either the frequentist or the Bayesian paradigm.

Roxane Du Berger - One of the best experts on this subject based on the ideXlab platform.

  • Some comments on Bayesian sample size determination
    The Statistician, 1995
    Co-Authors: Lawrence Joseph, David B. Wolfson, Roxane Du Berger
    Abstract:

    SUMMARY Several criteria for Bayesian sample size determination have recently been proposed. Criteria based on highest posterior density (HPD) intervals from the exact posterior distribution in general lead to smaller sample sizes than those based on non-HPD intervals and/or normal approximations to the exact density. The economies are variable, however, and depend both on the prior inputs and the desired posterior accuracy and coverage probability. In our reply we review several properties of sample size methods and discuss the importance of these properties in the context of a Binomial Experiment. A general algorithm for Bayesian sample size determination that is useful for more complex sampling situations based on Monte Carlo simulations is briefly described.

  • Sample Size Calculations for Binomial Proportions Via Highest Posterior Density Intervals
    The Statistician, 1995
    Co-Authors: Lawrence Joseph, David B. Wolfson, Roxane Du Berger
    Abstract:

    Three different Bayesian approaches to sample size calculations based on highest posterior density (HPD) intervals are discussed and illustrated in the context of a Binomial Experiment. The preposterior marginal distribution of the data is used to find the sample size needed to attain an expected HPD coverage probability for a given fixed interval length. Alternatively, one can find the sample size required to attain an expected HPD interval length for a fixed coverage. These two criteria can lead to different sample size requirements. In addition to averaging, a worst possible outcome scenario is also considered. The results presented here provide an exact solution to a problem recently addressed in the literature.

Bento Collares Gonçalves - One of the best experts on this subject based on the ideXlab platform.

  • Is hearing believing? Patterns of bird voice misidentification in an online quiz
    Revista Brasileira de Ornitologia, 2016
    Co-Authors: Bento Collares Gonçalves, Gonçalo Ferraz
    Abstract:

    This study aims to uncover patterns of species identification error in bioacoustic surveys of central Amazon birds. To quantify errors, we developed an on-line quiz based on vocalizations of an undisclosed set of 41 antbird (Thamnophilidae) and woodcreeper (Dendrocolaptinae) species. We invited experts to answer the quiz and obtained 820 answers from 20 participants. The answers were compared to the results of a Binomial Experiment with a success probability of 0.5; i.e. we examined whether participants identified species correctly more often than expected by the toss of a coin with a 50% chance of producing the right identification. We also examined whether species were correctly identified more often than expected under a similar coin toss Experiment. Quiz answers were compiled in a triangular matrix showing species ranked by taxonomic order on both axes. From the triangular matrix we can ask whether closely-related species were mistaken for each other, i.e. confused, more often than distantly- related species. We tested this hypothesis with a null model approach that compared the mean taxonomic distance between confused species in the observed matrix to the distribution of mean taxonomic distances between confused species in 10,000 randomized matrices. Finally, we drew a dendrogram to represent the similarity between species with regard to the distribution of identification errors. The 20 participants who took the quiz showed substantial variation in their ability to identify species correctly. Fourteen species were correctly identified more often than expected at random, while only one was misidentified more often than expected at random. The observed mean distance between confused species was smaller than all of the mean distances from the randomized, null-model matrices, indicating that confusions are more frequent between closely related species than between distant ones.

  • Is hearing believing? Patterns of bird voice misidentification in an online quiz
    Revista Brasileira de Ornitologia, 2016
    Co-Authors: Bento Collares Gonçalves, Gonçalo Ferraz
    Abstract:

    This study aims to uncover patterns of species identification error in bioacoustic surveys of central Amazon birds. To quantify errors, we developed an on-line quiz based on vocalizations of an undisclosed set of 41 antbird (Thamnophilidae) and woodcreeper (Dendrocolaptinae) species. We invited experts to answer the quiz and obtained 820 answers from 20 participants. The answers were compared to the results of a Binomial Experiment with a success probability of 0.5; i.e. we examined whether participants identified species correctly more often than expected by the toss of a coin with a 50% chance of producing the right identification. We also examined whether species were correctly identified more often than expected under a similar coin toss Experiment. Quiz answers were compiled in a triangular matrix showing species ranked by taxonomic order on both axes. From the triangular matrix we can ask whether closely-related species were mistaken for each other, i.e. confused, more often than distantly-related species. We tested this hypothesis with a null model approach that compared the mean taxonomic distance between confused species in the observed matrix to the distribution of mean taxonomie distances between confused species in 10,000 randomized matrices. Finally, we drew a dendrogram to represent the similarity between species with regard to the distribution of identification errors. The 20 participants who took the quiz showed substantial variation in their ability to identify species correctly. Fourteen species were correctly identified more often than expected at random, while only one was misidentified more often than expected at random. The observed mean distance between confused species was smaller than all of the mean distances from the randomized, null-model matrices, indicating that confusions are more frequent between closely related species than between distant ones.

Maheswari Subbiah - One of the best experts on this subject based on the ideXlab platform.

  • proportion a comprehensive r package for inference on single Binomial proportion and bayesian computations
    SoftwareX, 2017
    Co-Authors: Maheswari Subbiah, V Rajeswaran
    Abstract:

    Abstract Extensive statistical practice has shown the importance and relevance of the inferential problem of estimating probability parameters in a Binomial Experiment; especially on the issues of competing intervals from frequentist, Bayesian, and Bootstrap approaches. The package written in the free R environment and presented in this paper tries to take care of the issues just highlighted, by pooling a number of widely available and well-performing methods and apporting on them essential variations. A wide range of functions helps users with differing skills to estimate, evaluate, summarize, numerically and graphically, various measures adopting either the frequentist or the Bayesian paradigm.