Triangle Sampling Based Estimation of Average Degree of Network Using Different Estimators
DOI:
https://doi.org/10.31305/rrijm.2022.v07.i05.004Keywords:
Graph, Sampling, Social network, Triangle, Ratio Estimator, Regression Estimator, Confidence interval(CI), Mean Squared Error(MSE), Bias, SimulationAbstract
Graphs are used to represent complex relationships which include online social networks, pandemic spread networks and other real world networks. In recent time, graph sampling has been used for the study of different parameters of networks. Such include many sampling algorithms like Random node, Random edge sampling, Rank degree etc. which are used for collection of subsets of a network, but efficient estimation methods are not discussed much for parameter estimation. This paper presents a comparison of different estimators comprises Ratio and Regression estimators to estimate the average degree of a network. Triangle sampling is used to collect sample data using seed nodes. A comparative procedure is used to obtain the lower and upper limits of confidence intervals with the help of multiple triangle samples. Ogive based simulation is also used for single value computation of both limits of confidence interval(CI). The results obtained from the simulation show that Regression estimator is more efficient than the Ratio in triangle sampling.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
This is an open access article under the CC BY-NC-ND license Creative Commons Attribution-Noncommercial 4.0 International (CC BY-NC 4.0).