Skip to content
This repository contains the software to
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
ExampleData
Implementation
LICENSE
README.md

README.md

Exponential trace model for networks of discrete and continuous data

This repository provides an implementation of the sampling-based approximation for computing the maximum likelihood estimator (MLE) of exponential trace model.

Usage

The file Implementation/exp_trace_model.R contains functions for computing the approximate maximum likelihood estimator. Our upcoming paper describes the algorithm in details.

We include an example code Implementation/example.R for analyzing neuron spike data. The neuron spike data is from Demas et al. 2003.

source("example.R")

Simulation

Running the simulation, as described in the paper, takes a long time and is recommended to be implemented on a cluster. We include small-scale example code in the repository.

Data-type specific functions can be found under Implementation/Data_type_specific.

Poisson analog data

source("Implementation/synthetic_Poisson_analog.R")

Exponential analog data

source("Implementation/synthetic_exponential_analog.R")

Composite of Poisson analog and Bernoulli data

source("Implementation/synthetic_Poisson_Bernoulli.R")

Composite of Poisson analog and Gaussian data

source("Implementation/synthetic_Poisson_Gaussian")

Repository Authors

  • Rui Zhuang — Ph.D. candidate in Biostatistics, University of Washington — methodology and R implementation
  • Noah Simon — Assistant Professor in Biostatistics, University of Washington — methodology
  • Johannes Lederer — Professor in Mathematical Statistics, Ruhr-University Bochum — methodology
You can’t perform that action at this time.