reap_freq: Determine reappearance frequency

In MrMaximumMax/FBCanalysis: Develop and evaluate time series data models based on fluctuation based clustering

Determine reappearance frequency

Description

Determine the reappearance frequency for clustered elements in perturbed data for specific amount of random data removal

Usage

reap_freq(plist, parameter, removal, n_simu, method, n_clust, Iter, normalize)

Arguments

plist	Object of type list storing patient time series data (also see function: patient_list)
parameter	Parameter of interest in time series data list
removal	Amount of random data removal to determine Jaccard index
n_simu	Number of simulations
method	Clustering method (also see function: clust_matrix)
n_clust	Number of clusters (also see function: clust_matrix)
Iter	Maximum iterations to determine Earth Mover's Distances (also see function: emd_matrix); default is 5,000 for this function
normalize	Indicates if parameter indicated needs to be normalized or not (TRUE by default)

Details

To begin, each participant's collection of measured values is randomly depleted of a certain proportion of measurements. The clustering technique is then performed using the perturbed data, and the resulting clusters are compared to the original clusters created with the unperturbed gold standard. This technique is done iteratively in order to provide statistics indicating the original clusters' stability following the elimination of random data. These stability statistics are calculated using two cluster similarity metrics: Jaccard's index, a measure of global similarity that quantifies the extent to which the original and modified clusters overlap. Additionally, it is utilized to decide which cluster is considered the cognate cluster. Then it was transformed into a local measure, meaning the frequency with which each member of the original clusters reappeared between iterations.

Value

Vector of length of n_simu where reappearance frequency is stored for each simulation run

References

Edgar Delgado-Eckert, Oliver Fuchs, Nitin Kumar, Juha Pekkanen, Jean-Charles Dalphin, Josef Riedler, Roger Lauener, Michael Kabesch, Maciej Kupczyk, Sven-Erik Dahlen, et al. Functional phenotypes determined by fluctuation-based clustering of lung function measurements in healthy and asthmatic cohort participants. Thorax, 73(2):107–115, 2018.

MrMaximumMax/FBCanalysis documentation built on June 23, 2022, 8:21 p.m.