Questions tagged [networks]
Refers to network theory as part of the graph theory. For questions about neural networks, use our [neural-networks] tag.
208
questions
0
votes
0answers
15 views
Hierarchical graph clustering using a kernel matrix in R
I have a set of 9 directed graphs of differing sizes and I'd like to use graph clustering to create a dendrogram illustrating their structural similarity, similar to what's done in the NetConfer ...
0
votes
0answers
6 views
degree centrality for two clusters in the network to identify most central influencers “unique” to each cluster
I have a network containing 2 groups of people A and B (taken from twitter).
I want to find the most influential people within each group but I want to make sure that these people are specific to ...
0
votes
0answers
6 views
Grouping nodes together that have no connection
We have a data set of 200 people and how much they have interacted with each other based on email metadata (collaboration hours = edge weight). We were asked to put people into 20 groups of 10 so that ...
0
votes
0answers
7 views
Edge weights as dependent variable in a network / dyadic data
Let's say that I have a network of countries that export to each other (directed edges: A to B, B to C, but not B to A).
Countries (vertices) have attributes, like their Human Development Index score, ...
1
vote
0answers
7 views
Methods to align/reduce distance between two or more 3D graph-spaces?
I'm trying to align multiple graphs of spatial data, similar to image registration, but on a 3D graphspace of a select feature. I have a bunch of point data with x,y,z coordinates that together, ...
0
votes
0answers
6 views
How can I compare interaction network's metrics from two samples?
I'm constructing interaction networks with bee-plant interaction data, using bipartite R package. I want to compare these interactions between two different seasons. In some papers they use a t-test, ...
0
votes
0answers
6 views
What network layout or clustering algorithms can handle a mix of negative and positive weights?
In particular, I would like to create a network from correlation data. The negative values should represent repulsive forces and positive values as attractive forces. Values close to 0 for weights ...
0
votes
0answers
10 views
Output for ERGM (Exponential Random Graph Model) is not correct
I really need some advice regarding running an exponential random graph model (ERGM) in R.
These are the two social networks that I am using.
First social network:
Second Social Network:
Now, this ...
2
votes
2answers
71 views
How do I evaluate correlation, that appears non-linear
Directed here from StackOverflow
Let's say I want to assess if there is a correlation between two fields, one of which I know to have a power distribution.
A lot of the information I read assumes ...
2
votes
0answers
18 views
Is a grid-like network more efficient than a random network?
Imagine two different types of street networks with the same number of nodes and where edges are weighted according to their length. Both network types cover the same geographic area (say 1km²) and ...
0
votes
0answers
10 views
binwidths/no. of bins when overlaying two histograms
Should the binwidths for two histograms be same or no. of bins in both histograms be same when they are overlayed for comparison? or there is no correlation? I am comparing histogram of centrality for ...
0
votes
0answers
6 views
Recommending without knowing the clusters
I've heard of some methods to produce recommendations based on clustering: if many of the users who enjoy A also enjoy B, and you enjoy A, then you are likely to enjoy B. A and B in this case form a "...
0
votes
0answers
17 views
Binwidths/no. of bins for 2 histograms for overlaying them
Should the binwidths for two histograms be same or no. of bins in both histograms be same when they are overlayed for comparison? or there is no correlation?
I am comparing histogram of centrality for ...
0
votes
0answers
18 views
Data Fusion Algorithms for Network or Graph Data
Let's suppose we have two distributions defined over graphs, $P_1(G)$, $P_2(G)$. For example, these could correspond to familiar distributions like Erdős–Rényi, Barabási–Albert, or Watts–Strogatz, or ...
0
votes
1answer
9 views
Network linkage formation prediction
Is there a statistical model that can study determinants of network linkage formation? For a set of companies (where we observe their industry, annual revenue, etc), we see which pairs are connected ...
2
votes
1answer
38 views
Degree and weight preserving randomisation in networks
I have a network in which nodes are highly interconnected (250 nodes where 90% of the nodes have degree = 249). The connections are weighted with a normalised index that goes from 0 to 1, where 1 ...
1
vote
1answer
19 views
How can I encode a network into a machine learning feature?
I am developing a predictive machine learning model. The dataset is social media posts from Twitter relating to a particular topic.
One of the features I would like to incorporate into the model is ...
2
votes
0answers
27 views
Intuition behind null model for disparity filter algorithm
I'm trying to better understand the disparity filter algorithm for weighted networks:
Original paper: https://www.pnas.org/content/106/16/6483
Wikipedia link: https://en.wikipedia.org/wiki/...
1
vote
1answer
32 views
ERGM with larger log-likelihood but worse fit than reference model?
I'm using the R package statnet to fit some ERGMs to the Faux Dixon High simulated network data provided with the package. The first model I fit is almost identical ...
0
votes
0answers
13 views
what is the probability that a randomly chosen vertex belong to a small component of size S?
I was reading chapter 12 of "Networks: An Introduction
Book by Mark Newman" about Random Graph. part 12.6 of the book is about the small components in Random Graph. page 405 equation 12.24 and 12.25 I ...
1
vote
0answers
9 views
What is constraint and effectivesize in structural holes?
Today, I spent the whole day trying to understand what structural holes in network means. More specifically I want to clarify what the two measurements constraint and effective size means? Is it good ...
0
votes
0answers
23 views
Why is my correlation matrix dropping that many NA?
I am trying to build a correlation matrix among documents per topic on a Latent Dirichlet Allocation model by text2vec, getting a doc_topic_distr matrix like below, with only first 5 documents, it's a ...
1
vote
0answers
40 views
Compare networks, including centrality measures, clustering/community detection results
Hi my fellow researchers, I am trying to compare two networks based on exactly same group of individuals (179 unique individuals):
One network is based on these individuals' meeting data (two-mode/...
1
vote
0answers
39 views
What is the difference between node clustering and network community detection?
Node clustering algorithms in which we attempt to determine dense regions of the graph based on edge behaviour(either be a distance value or a similarity value). The more similar nodes come together ...
2
votes
1answer
74 views
Network analysis: Formal definition of the number of 1st order neighbours of degree 1
I am looking for a formal definition of a network metric I am using in a scientific article. Let $i$ be a vertex in a graph $G$ and $N(i)$ are the first order neighbors of vertex $i$. I am interested ...
0
votes
1answer
55 views
Calculating the Expected life of network with hazard functions
I have been asked to solve some questions in the statistical program R.
First, I want to find the expected life length (by numeric integration) of a network with 3 parallel components (T1,T2,T3) and ...
1
vote
0answers
72 views
How can I visualize and cluster weighted graphs in python?
On any ecommerce website, you have options to apply filters to filter out products. For example:
So I have data of how many users applied what filters tuples on the website. Which is fetched from ...
0
votes
0answers
16 views
Null model of a random network formula derivation
This paper generates backbones in a network using a null model. The paper mentions
https://arxiv.org/pdf/0904.2389.pdf
"The null model that we use to define anomalous
fluctuations provides the ...
0
votes
0answers
87 views
What is the difference of first-order difference and second-order difference in trend analysis?
I have seen that the literature in trend analysis use first-order difference and ...
1
vote
0answers
21 views
Regression with autocorrelation given by a graph
Supppose I would like to fit a standard regression model of the form $y = \alpha + X \beta + \epsilon$, but my observations come from a networked population (eg. social network). I have the graph $G$ ...
0
votes
0answers
22 views
Help wrapping my head around an analysis based on social networks
I should preface this with a slight disclaimer. The scenario I have outlined is not actually the data I am working with, it is an analogy that I have created (hopefully accounting for all important ...
1
vote
0answers
34 views
Summary statistics for bipartite networks
I have a large bipartite network that I would like to summarise. So far, I have found the following summary statistics:
Degree centrality
Graph density
Modularity
Nestedness
I have not found a ...
2
votes
0answers
35 views
Reference request: Network/graph topology inference
I am a mathematician looking for a survey/book on methods for inference of graph/network topology (structure). Specifically, the kind of problem I am looking to study is as follows:
Given a graph $...
0
votes
1answer
103 views
Network analysis - Correlation is positive and significant, but coefficient of simple logistic regression is not significant?
I have an adjacency matrix and another which represents whether the two nodes share an attribute. Consider it like an homophily test. We want to test if the likelihood to form a connect depends on the ...
1
vote
2answers
46 views
Missing values in a variable depending on the values of another variable
I'm working on a public procurement dataset where I have information on all the participants that presented offers in 358 tenders. I'm analysing relationships between all the companies of the dataset (...
1
vote
2answers
37 views
representative nodes in modular network
I want to find the most representative nodes in each module in a modular network. I have used the Louvain algorithm on my graph and found two main modules. Now I want to know what nodes are the most ...
1
vote
1answer
45 views
“Multi-level” social network analysis?
I am very new to social network analysis and working on a project here that I am not sure what's possible to model.
I don't want to quite call this multi-level because I am not exactly looking at ...
1
vote
1answer
23 views
Finding the effect of nodes on a density heatmap
Let's say I have a geo-tagged dataset of all payment transactions for businesses in a city. I know whether each payment is made by cash or card, and have made a heatmap of where in the city the ...
1
vote
1answer
43 views
How to obtain the statistical significance of a given community structure for a directed network?
So, I have several directed (multi-edged) networks, and within them each node has been assigned to one of seven categories (based on some a priori circumstances). Each category should have a higher ...
0
votes
0answers
27 views
Visual representation of strong associations of two categorical variables
I have a dataset of one categoric variable "supermarket" for each individual person and multiple "product" categories per person and supermarket.
E.g.:
Person 1 went shopping in supermarket X and ...
0
votes
1answer
98 views
Which regression used for normalized count data
I am working with social network data. I have multiple networks of various sizes and I'm calculating indegree (the number of connections between people) in each of the networks. I've been told to ...
0
votes
1answer
21 views
Determining the closeness of nodes by their neighbours
Background
I have a directional network that is comprised of two types of nodes, business_sector nodes, and event_type nodes. ...
4
votes
2answers
102 views
Order of Conditional Independence Tests
I'm studying the PC algorithm for learning the structure of a Bayesian Network.
One of the steps refers to performing several rounds of conditional independence tests of increasing order, zero, first,...
-1
votes
1answer
258 views
How to cluster a (directional) dissimilarity matrix with both positive and negative values?
I may be thinking of this incorrectly but what would be the best way to cluster a dissimilarity measure that has direction?
For example, if someone had condition A ...
0
votes
1answer
45 views
Predict node attribute from network variables
ERGM models the probability of a tie forming in a network. Is there a way of using ERGM, or an equivalent model, where the response variable is an attribute of the node, not a tie? Basically, turning ...
0
votes
0answers
182 views
Compare the degree distribution of a real networks and multiple random networks
Before the paper real world networks are rarely scale free, studies used to (still do) check for the slope in degree distribution graphs and if the slope fell between 2 and 3, discern that the network ...
2
votes
1answer
51 views
shortest path optimization for multiple edge attributes
Say I have a network. The edges each have two attributes: age and height. How might I run a shortest path algorithm that optimizes on both age and height? And could I weight it so that it optimizes 0....
0
votes
0answers
20 views
Compare treatment effects across Levels of aggregation
Suppose I am running an experiment to see if a treatment changes the mean weight of a group of people. Note that I am specifically interested in the mean weight: if half the people get heavier, and ...
1
vote
1answer
504 views
Centrality of a directed network with edge weights - Gephi
I have the following network of court judgments in the form of a big network.(50k+ nodes and 100k+ edges with weight values). The size is the number of citations. The idea is that court judgments work ...
1
vote
1answer
788 views
Assortativity coefficient in igraph
In the context of Social Network Analysis, I want to compute the homogeneity of different networks for specific attributes. For this case the igraph package contains the method assortativity() to ...
