scholarly journals Common datastream permutations of animal social network data are not appropriate for hypothesis testing using regression models

2020 ◽  
Author(s):  
Michael N. Weiss ◽  
Daniel W. Franks ◽  
Lauren J. N. Brent ◽  
Samuel Ellis ◽  
Matthew J. Silk ◽  
...  
Keyword(s):  
Social Network ◽  
Social Structure ◽  
Null Hypothesis ◽  
Regression Models ◽  
Error Rates ◽  
Network Data ◽  
Type I ◽  
List Type ◽  
False Positive Error ◽  
The Social

AbstractSocial network methods have become a key tool for describing, modelling, and testing hypotheses about the social structures of animals. However, due to the non-independence of network data and the presence of confounds, specialized statistical techniques are often needed to test hypotheses in these networks. Datastream permutations, originally developed to test the null hypothesis of random social structure, have become a popular tool for testing a wide array of null hypotheses. In particular, they have been used to test whether exogenous factors are related to network structure by interfacing these permutations with regression models.Here, we show that these datastream permutations typically do not represent the null hypothesis of interest to researchers interfacing animal social network analysis with regression modelling, and use simulations to demonstrate the potential pitfalls of using this methodology.Our simulations show that utilizing common datastream permutations to test the coefficients of regression models can lead to extremely high type I (false-positive) error rates (> 30%) in the presence of non-random social structure. The magnitude of this problem is primarily dependent on the degree of non-randomness within the social structure and the intensity of samplingWe strongly recommend against utilizing datastream permutations to test regression models in animal social networks. We suggest that a potential solution may be found in regarding the problems of non-independence of network data and unreliability of observations as separate problems with distinct solutions.

scholarly journals Kinship does not predict the structure of a shark social network

2019 ◽  
Author(s):  
Johann Mourier ◽  
Serge Planes
Keyword(s):  
Social Network ◽  
Social Structure ◽  
Marine Mammals ◽  
Social Preferences ◽  
Genetic Relatedness ◽  
Error Rates ◽  
Type I ◽  
The Social ◽  
Social Associations

ABSTRACTGenetic relatedness in animal societies is often a factor that drives the structure of social groups. In the marine world, most studies which have investigated this question have focused on marine mammals such as whales and dolphins. For sharks, recent studies have demonstrated preferential associations among individuals from which social communities emerge. Assortment patterns have been found according to phenotypic or behavioural traits but the role of genetic relatedness in shaping the social structure of adult shark populations has, to the best our knowledge, never been investigated. Here, we used a social network analysis crossed with DNA microsatellite genotyping to investigate the role of the genetic relatedness in the social structure of a blacktip reef shark (Carcharhinus melanopterus) population. Based on data from 156 groups of sharks, we used generalized affiliation indices to isolate social preferences from non-social associations, controlling for the contribution of sex, size, gregariousness, spatial and temporal overlap on social associations, to test for the influence of genetic relatedness on social structure. A double permutation procedure was employed to confirm our results and account for issues arising from potentially elevated type I and type II error rates. Kinship was not a predictor of associations and affiliations among sharks at the dyad or community levels as individuals tended to associate independently of the genetic relatedness among them. The lack of parental care in this species may contribute to the breakdown of family links in the population early in life, thereby preventing the formation of kin-based social networks.

The Multilevel p2 Model

Methodology ◽  
2006 ◽  
Vol 2 (1) ◽  
pp. 42-47 ◽  
Author(s):  
Bonne J. H. Zijlstra ◽  
Marijtje A. J. van Duijn ◽  
Tom A. B. Snijders
Keyword(s):  
Social Network ◽  
Network Data ◽  
Mcmc Algorithm ◽  
Independent Observation ◽  
Single Observation ◽  
Multiple Networks ◽  
Social Network Data ◽  
Multiple Observations ◽  
Practical Support ◽  
The Social

The p 2 model is a random effects model with covariates for the analysis of binary directed social network data coming from a single observation of a social network. Here, a multilevel variant of the p 2 model is proposed for the case of multiple observations of social networks, for example, in a sample of schools. The multilevel p 2 model defines an identical p 2 model for each independent observation of the social network, where parameters are allowed to vary across the multiple networks. The multilevel p 2 model is estimated with a Bayesian Markov Chain Monte Carlo (MCMC) algorithm that was implemented in free software for the statistical analysis of complete social network data, called StOCNET. The new model is illustrated with a study on the received practical support by Dutch high school pupils of different ethnic backgrounds.

Duality beyondPersons and Groups

2020 ◽  
pp. 391-413
Author(s):  
Sophie Mützel ◽  
Ronald Breiger
Keyword(s):  
Social Network ◽  
Social Network Analysis ◽  
Network Analysis ◽  
Network Data ◽  
Future Directions ◽  
Affiliation Networks ◽  
The Social ◽  
Recent Developments ◽  
Principle Of Duality ◽  
Seminal Article

This chapter focuses on the general principle of duality, which was originally introduced by Simmel as the intersection of social circles. In a seminal article, Breiger formalized Simmel’s idea, showing how two-mode types of network data can be transformed into one-mode networks. This formal translation proved to be fundamental for social network analysis, which no longer needed data on who interacted with whom but could work with other types of data. In turn, it also proved fundamental for the analysis of how the social is structured in general, as many relations are dual (e.g. persons and groups, authors and articles, organizations and practices), and are thus susceptible to an analysis according to duality principles. The chapter locates the concept of duality within past and present sociology. It also discusses the use of duality in the analysis of culture as well as in affiliation networks. It closes with recent developments and future directions.

scholarly journals Designing Educational Analytics Tools Using Visualization Based on Behavioral, Motivational, and Social Network Data

2019 ◽  
pp. 81-93
Author(s):  
Iliya L. Musabirov ◽  
Keyword(s):  
Social Network ◽  
Social Values ◽  
Network Data ◽  
Network Approach ◽  
Social Network Data ◽  
Use Of Data ◽  
University Courses ◽  
The Social ◽  
Social Network Approach ◽  
Visualization Tools

The article presents a description of the approach to the use of data visualization in various educational Analytics tools when building University courses. In addition to the analysis of educational behavior, socio-psychological approaches, including the theory of expectations and social values, and the social network approach, are separately considered as prospects for analysis. An example of designing training Analytics using modern data analysis and visualization tools is analyzed.

Influential Nodes in Social Networks

2020 ◽  
pp. 371-385
Author(s):  
Kousik Das ◽  
Rupkumar Mahapatra ◽  
Sovan Samanta ◽  
Anita Pal
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Social Structure ◽  
The Social ◽  
Different Types ◽  
Influential Nodes

Social network is the perfect place for connecting people. The social network is a social structure formed by a set of nodes (persons, organizations, etc.) and a set of links (connection between nodes). People feel very comfortable to share news and information through a social network. This chapter measures the influential persons in different types of online and offline social networks.

Social Network Analysis in Marketing

E-Marketing ◽  
2012 ◽  
pp. 185-197
Author(s):  
Przemyslaw Kazienko ◽  
Piotr Doskocz ◽  
Tomasz Kajdanowicz
Keyword(s):  
Social Network ◽  
Social Network Analysis ◽  
Network Analysis ◽  
Social Relationships ◽  
Network Data ◽  
Social Network Data ◽  
The Social ◽  
Targeted Marketing ◽  
Potential Customers ◽  
Demographic Features

The chapter describes a method how to perform a classification task without any demographic features and based only on the social network data. The concept of such collective classification facilitates to identify potential customers by means of services used or products purchased by the current customers, i.e. classes they belong to as well as using social relationships between the known and potential customers. As a result, a personalized offer can be prepared for the new clients. This innovative marketing method can boost targeted marketing campaigns.

Social Network Analysis in Marketing

2011 ◽  
pp. 271-283
Author(s):  
Przemyslaw Kazienko ◽  
Piotr Doskocz ◽  
Tomasz Kajdanowicz
Keyword(s):  
Social Network ◽  
Social Network Analysis ◽  
Network Analysis ◽  
Social Relationships ◽  
Network Data ◽  
Social Network Data ◽  
The Social ◽  
Targeted Marketing ◽  
Potential Customers ◽  
Demographic Features

The chapter describes a method how to perform a classification task without any demographic features and based only on the social network data. The concept of such collective classification facilitates to identify potential customers by means of services used or products purchased by the current customers, i.e. classes they belong to as well as using social relationships between the known and potential customers. As a result, a personalized offer can be prepared for the new clients. This innovative marketing method can boost targeted marketing campaigns.

scholarly journals The performance of permutations and exponential random graph models when analyzing animal networks

2020 ◽  
Vol 31 (5) ◽  
pp. 1266-1276 ◽  
Author(s):  
Julian C Evans ◽  
David N Fisher ◽  
Matthew J Silk
Keyword(s):  
Social Network ◽  
Random Graph ◽  
False Positive ◽  
False Negative ◽  
Error Rates ◽  
Network Data ◽  
Exponential Random Graph Models ◽  
Graph Models ◽  
Random Graph Models ◽  
Exponential Random Graph

Abstract Social network analysis is a suite of approaches for exploring relational data. Two approaches commonly used to analyze animal social network data are permutation-based tests of significance and exponential random graph models. However, the performance of these approaches when analyzing different types of network data has not been simultaneously evaluated. Here we test both approaches to determine their performance when analyzing a range of biologically realistic simulated animal social networks. We examined the false positive and false negative error rate of an effect of a two-level explanatory variable (e.g., sex) on the number and combined strength of an individual’s network connections. We measured error rates for two types of simulated data collection methods in a range of network structures, and with/without a confounding effect and missing observations. Both methods performed consistently well in networks of dyadic interactions, and worse on networks constructed using observations of individuals in groups. Exponential random graph models had a marginally lower rate of false positives than permutations in most cases. Phenotypic assortativity had a large influence on the false positive rate, and a smaller effect on the false negative rate for both methods in all network types. Aspects of within- and between-group network structure influenced error rates, but not to the same extent. In "grouping event-based" networks, increased sampling effort marginally decreased rates of false negatives, but increased rates of false positives for both analysis methods. These results provide guidelines for biologists analyzing and interpreting their own network data using these methods.

Introduction

2020 ◽  
pp. 1-29
Keyword(s):  
Social Network ◽  
Social Network Analysis ◽  
Network Analysis ◽  
Social Structure ◽  
Research Methods ◽  
The Other ◽  
Traditional Research ◽  
The Social ◽  
Social Realm ◽  
The Impact

The traditional research approaches common in different disciplines of social sciences centered around one half of the social realm: the actors. The other half are the relations established by these actors and forming the basis of “social.” The social structure shaped by these relations, the position of the actor within this structure, and the impact of this position on the actor are mostly excluded by the traditional research methods. In this chapter, the authors introduce social network analysis and how it complements the other methods.

scholarly journals Considering Both Statistical and Clinical Significance

2016 ◽  
Vol 5 (5) ◽  
pp. 16 ◽  
Author(s):  
Guolong Zhao
Keyword(s):  
Clinical Significance ◽  
Null Hypothesis ◽  
Type I Error ◽  
Statistical Significance ◽  
Error Rates ◽  
Type I ◽  
Data Set ◽  
Type I Error Rates ◽  
Empirical Coverage ◽  
Superiority Trials

To evaluate a drug, statistical significance alone is insufficient and clinical significance is also necessary. This paper explains how to analyze clinical data with considering both statistical and clinical significance. The analysis is practiced by combining a confidence interval under null hypothesis with that under non-null hypothesis. The combination conveys one of the four possible results: (i) both significant, (ii) only significant in the former, (iii) only significant in the latter or (iv) neither significant. The four results constitute a quadripartite procedure. Corresponding tests are mentioned for describing Type I error rates and power. The empirical coverage is exhibited by Monte Carlo simulations. In superiority trials, the four results are interpreted as clinical superiority, statistical superiority, non-superiority and indeterminate respectively. The interpretation is opposite in inferiority trials. The combination poses a deflated Type I error rate, a decreased power and an increased sample size. The four results may helpful for a meticulous evaluation of drugs. Of these, non-superiority is another profile of equivalence and so it can also be used to interpret equivalence. This approach may prepare a convenience for interpreting discordant cases. Nevertheless, a larger data set is usually needed. An example is taken from a real trial in naturally acquired influenza.

Sign in / Sign up

Export Citation Format

Share Document