scholarly journals Likelihood-based approach to discriminate mixtures of network models that vary in time

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Naomi A. Arnold ◽  
Raul J. Mondragón ◽  
Richard G. Clegg
Keyword(s):  
Network Model ◽  
Change Point ◽  
Network Science ◽  
Preferential Attachment ◽  
Network Models ◽  
Explanatory Models ◽  
Growth Mechanisms ◽  
Artificial Data ◽  
Network Growth ◽  
Over Time

AbstractDiscriminating between competing explanatory models as to which is more likely responsible for the growth of a network is a problem of fundamental importance for network science. The rules governing this growth are attributed to mechanisms such as preferential attachment and triangle closure, with a wealth of explanatory models based on these. These models are deliberately simple, commonly with the network growing according to a constant mechanism for its lifetime, to allow for analytical results. We use a likelihood-based framework on artificial data where the network model changes at a known point in time and demonstrate that we can recover the change point from analysis of the network. We then use real datasets and demonstrate how our framework can show the changing importance of network growth mechanisms over time.

scholarly journals Friendship paradox in growth networks: analytical and empirical analysis

2021 ◽  
Vol 6 (1) ◽  
Author(s):  
Sergei P. Sidorov ◽  
Sergei V. Mironov ◽  
Alexey A. Grigoriev
Keyword(s):  
Real World ◽  
Preferential Attachment ◽  
Empirical Studies ◽  
Mean Field ◽  
Network Models ◽  
Average Degree ◽  
Closure Model ◽  
Triadic Closure ◽  
Attachment Mechanism ◽  
Over Time

AbstractMany empirical studies have shown that in social, citation, collaboration, and other types of networks in real world, the degree of almost every node is less than the average degree of its neighbors. This imbalance is well known in sociology as the friendship paradox and states that your friends are more popular than you on average. If we introduce a value equal to the ratio of the average degree of the neighbors for a certain node to the degree of this node (which is called the ‘friendship index’, FI), then the FI value of more than 1 for most nodes indicates the presence of the friendship paradox in the network. In this paper, we study the behavior of the FI over time for networks generated by growth network models. We will focus our analysis on two models based on the use of the preferential attachment mechanism: the Barabási–Albert model and the triadic closure model. Using the mean-field approach, we obtain differential equations describing the dynamics of changes in the FI over time, and accordingly, after obtaining their solutions, we find the expected values of this index over iterations. The results show that the values of FI are decreasing over time for all nodes in both models. However, for networks constructed in accordance with the triadic closure model, this decrease occurs at a much slower rate than for the Barabási–Albert graphs. In addition, we analyze several real-world networks and show that their FI distributions follow a power law. We show that both the Barabási–Albert and the triadic closure networks exhibit the same behavior. However, for networks based on the triadic closure model, the distributions of FI are more heavy-tailed and, in this sense, are closer to the distributions for real networks.

scholarly journals Emerging, crystalizing, and changing psychological contracts over time: Introducing the iPC-network model

2019 ◽  
Author(s):  
Tim Vantilborgh
Keyword(s):  
Network Model ◽  
Psychological Contract ◽  
Dynamic Network ◽  
Network Models ◽  
Psychological Contracts ◽  
Exchange Relationships ◽  
Contract Breach ◽  
Alternative Approach ◽  
The Individual ◽  
Over Time

This chapter introduces the individual Psychological Contract (iPC) network model as an alternative approach to study psychological contracts. This model departs from the basic idea that a psychological contract forms a mental schema containing obligated inducements and contributions, which are exchanged for each other. This mental schema is captured by a dynamic network, in which the nodes represent the inducements and contributions and the ties represent the exchanges. Building on dynamic systems theory, I propose that these networks evolve over time towards attractor states, both at the level of the network structure and at the level of the nodes (i.e., breach and fulfilment attractor states). I highlight how the iPC-network model integrates recent theoretical developments in the psychological contract literature and explain how it may advance scholars understanding of exchange relationships. In particular, I illustrate how iPC-network models allow researchers to study the actual exchanges in the psychological contract over time, while acknowledging its idiosyncratic nature. This would allow for more precise predictions of psychological contract breach and fulfilment consequences and explains how content and process of the psychological contract continuously influence each other.

scholarly journals Studying Statistics Anxiety Requires Sound Statistics: A Comment on Siew, McCartney, and Vitevitch (2019)

2019 ◽  
Author(s):  
Fabian Dablander ◽  
Sacha Epskamp ◽  
Jonas M B Haslbeck
Keyword(s):  
Data Analysis ◽  
Statistical Model ◽  
Network Model ◽  
Network Science ◽  
Network Models ◽  
Statistics Anxiety ◽  
Scientific Disciplines ◽  
Statistics Course ◽  
Relevant Topic ◽  
Using Data

Empirical scientists cannot do without statistics. This fact is reflected by the pervasiveness of statistics courses in the curricula of essentially all scientific disciplines. Unfortunately, many students exhibit statistics anxiety, that is, ''feelings of anxiety [...] when taking a statistics course or doing statistical analyses'' (Cruise, Cash, & Bolton, 1985, p. 92). In a recent publication, Siew, McCartney, & Vitevitch (2019) aim to shed new light on this highly relevant topic by using data analysis tools from the field of network science. However, just as with any other statistical model, one has to carefully assess the adequacy and robustness of a network model. In this commentary, we point to a number of shortcomings in the article by Siew et al. (2019) with respect to this goal that question their main conclusions. We explain each problem and suggest ways to address it. We hope that these suggestions help to put future investigation of statistics anxiety using network models on a firm methodological basis.

scholarly journals An investigation of network growth principles in the phonological language network

2020 ◽  
Author(s):  
Cynthia S. Q. Siew ◽  
Michael Vitevitch
Keyword(s):  
Learning Outcomes ◽  
Preferential Attachment ◽  
Language Disorders ◽  
Age Of Acquisition ◽  
Network Growth ◽  
Phonological Representations ◽  
New Words ◽  
Lexical Representations ◽  
Over Time ◽  
Language Network

This paper investigated how network growth algorithms—preferential attachment, preferential acquisition, and lure of the associates—relate to the acquisition of words in the phonological language network, where edges are placed between words that are phonologically similar to each other. Through an archival analysis of age-of-acquisition norms from English and Dutch and word learning experiments, we examined how new words were added to the phonological network. Across both approaches, we found converging evidence that an inverse variant of preferential attachment—where new nodes were instead more likely to attach to existing nodes with few connections—influenced the growth of the phonological network. We suggest that the inverse preferential attachment principle reflects the constraints of adding new phonological representations to an existing language network with already many phonologically similar representations, possibly reflecting the pressures associated with the processing costs of retrieving lexical representations that have many phonologically similar competitors. These results contribute toward our understanding of how the phonological language network grows over time and could have implications for the learning outcomes of individuals with language disorders.

scholarly journals Flexible model selection for mechanistic network models

2019 ◽  
Vol 8 (2) ◽  
Author(s):  
Sixing Chen ◽  
Antonietta Mira ◽  
Jukka-Pekka Onnela
Keyword(s):  
Model Selection ◽  
Network Model ◽  
Statistical Models ◽  
Learning Algorithm ◽  
Large Body ◽  
Network Models ◽  
Mechanistic Models ◽  
Network Growth ◽  
Yeast Saccharomyces Cerevisiae ◽  
Selection For

Abstract Network models are applied across many domains where data can be represented as a network. Two prominent paradigms for modelling networks are statistical models (probabilistic models for the observed network) and mechanistic models (models for network growth and/or evolution). Mechanistic models are better suited for incorporating domain knowledge, to study effects of interventions (such as changes to specific mechanisms) and to forward simulate, but they typically have intractable likelihoods. As such, and in a stark contrast to statistical models, there is a relative dearth of research on model selection for such models despite the otherwise large body of extant work. In this article, we propose a simulator-based procedure for mechanistic network model selection that borrows aspects from Approximate Bayesian Computation along with a means to quantify the uncertainty in the selected model. To select the most suitable network model, we consider and assess the performance of several learning algorithms, most notably the so-called Super Learner, which makes our framework less sensitive to the choice of a particular learning algorithm. Our approach takes advantage of the ease to forward simulate from mechanistic network models to circumvent their intractable likelihoods. The overall process is flexible and widely applicable. Our simulation results demonstrate the approach’s ability to accurately discriminate between competing mechanistic models. Finally, we showcase our approach with a protein–protein interaction network model from the literature for yeast (Saccharomyces cerevisiae).

scholarly journals A network model of retrieval failures: Moving forward with incorporating clinical data

2021 ◽  
Author(s):  
Nichol Castro
Keyword(s):  
Clinical Practice ◽  
Network Model ◽  
Clinical Data ◽  
Network Science ◽  
Cognitive Model ◽  
Network Models ◽  
Language Disorders ◽  
Methodological Issues ◽  
Retrieval Failure

Understanding retrieval failures requires a cognitive model that considers not just impaired processes, but also the role of structure. The development of a network model of retrieval failures requires the inclusion of clinical data, but there remain methodological issues in using and interpreting such data: locus of retrieval failure, heterogeneity of individuals, and progression of disorder/disease. Techniques from network science may prove useful in addressing these issues, while capturing the complexity of language disorders. Critically, any network model we employ could have downstream impact on clinical practice, which ultimately impacts patient lives, harkening the need for theoretically well-informed network models.

scholarly journals Investigating the Influence of Inverse Preferential Attachment on Network Development

Entropy ◽  
2020 ◽  
Vol 22 (9) ◽  
pp. 1029
Author(s):  
Cynthia S. Q. Siew ◽  
Michael S. Vitevitch
Keyword(s):  
Growth Mechanism ◽  
Simulation Study ◽  
Preferential Attachment ◽  
Phonological Similarity ◽  
Network Development ◽  
Growth Mechanisms ◽  
Network Growth ◽  
New Words ◽  
Path Lengths ◽  
Power Law Distributions

Recent work investigating the development of the phonological lexicon, where edges between words represent phonological similarity, have suggested that phonological network growth may be partly driven by a process that favors the acquisition of new words that are phonologically similar to several existing words in the lexicon. To explore this growth mechanism, we conducted a simulation study to examine the properties of networks grown by inverse preferential attachment, where new nodes added to the network tend to connect to existing nodes with fewer edges. Specifically, we analyzed the network structure and degree distributions of artificial networks generated via either preferential attachment, an inverse variant of preferential attachment, or combinations of both network growth mechanisms. The simulations showed that network growth initially driven by preferential attachment followed by inverse preferential attachment led to densely-connected network structures (i.e., smaller diameters and average shortest path lengths), as well as degree distributions that could be characterized by non-power law distributions, analogous to the features of real-world phonological networks. These results provide converging evidence that inverse preferential attachment may play a role in the development of the phonological lexicon and reflect processing costs associated with a mature lexicon structure.

Can Network Models Represent Personality Structure and Processes Better than Trait Models Do?

2012 ◽  
Vol 26 (4) ◽  
pp. 444-445 ◽  
Author(s):  
Tobias Rothmund ◽  
Anna Baumert ◽  
Manfred Schmitt
Keyword(s):  
Network Model ◽  
Explanatory Power ◽  
Network Models ◽  
Personality Structure ◽  
Psychological Processes ◽  
Target Article ◽  
Flexible Framework ◽  
Trait Model ◽  
Better Than

We argue that replacing the trait model with the network model proposed in the target article would be immature for three reasons. (i) If properly specified and grounded in substantive theories, the classic state–trait model provides a flexible framework for the description and explanation of person × situation transactions. (ii) Without additional substantive theories, the network model cannot guide the identification of personality components. (iii) Without assumptions about psychological processes that account for causal links among personality components, the concept of equilibrium has merely descriptive value and lacks explanatory power. Copyright © 2012 John Wiley & Sons, Ltd.

scholarly journals Firm’s strategic choices and network knowledge dynamics: how do they affect innovation?

2018 ◽  
Vol 22 (1) ◽  
pp. 1-20 ◽  
Author(s):  
Jose Antonio Belso-Martinez ◽  
Isabel Diez-Vial
Keyword(s):  
Absorptive Capacity ◽  
Knowledge Networks ◽  
Knowledge Network ◽  
Strategic Choices ◽  
Network Growth ◽  
Content Type ◽  
Endogenous Factors ◽  
The Impact ◽  
Innovative Capacity ◽  
Over Time

Purpose This paper aims to explain how the evolution of knowledge networks and firms’ strategic choices affect innovation. Endogenous factors associated with a path-dependent evolution of the knowledge network are jointly considered with a firm’s development of international relationships and increasing internal absorptive capacity over time. Design/methodology/approach In a biotech cluster, the authors gathered data on the firms’ characteristics and network relationships by asking about the technological knowledge they received in the cluster in 2007 and 2012 – “roster-recall” method. Estimation results were obtained using moderated regression analysis. Findings Firms that increase their involvement in knowledge networks over time also tend to increase their innovative capacity. However, efforts devoted to building international links or absorptive capacity negatively moderate the impact of network growth on innovation. Practical implications Practitioners have two alternative ways of increasing innovation inside knowledge networks: they can increase their centrality by developing their knowledge network interactions or invest in developing their internal absorptive capacity and new international sources of knowledge. Investing in both of these simultaneously does not seem to improve a firm’s innovative capacity. Originality/value Coupling firms’ strategic options with knowledge network dynamics provide a more complete way of explaining how firms can improve their innovative capacity.

Sign in / Sign up

Export Citation Format

Share Document