Software

RDS Analyst is a software package for the analysis of Respondent-driven sampling (RDS) data that implements recent advances in statistical methods. RDS Analyst has an easy-to-use graphical user interface to the powerful and sophisticated capabilities of the computer package R. It provides a comprehensive framework for working with RDS data, including tools for sample and population estimations, testing, confidence intervals and sensitivity analysis.
For more information, see the Hard-to-Reach Population Methods Research Group website.

For more information on Relative Distribution Methods, including the preface to the book, data sets, and software to implement the methods are available from the Relative Distribution website.
The main software is the R software package reldist: Tools for the comparison of distributions. This includes nonparametric estimation of the relative distribution PDF and CDF and numerical summaries as described in Relative Distribution Methods in the Social Sciences by Mark S. Handcock and Martina Morris.

The R software package rpm that estimates revealed preference models from data collected on bipartite matchings. The models are for matchings within a bipartite population where individuals have utility for people based on known and unknown characteristics. People can form a partnership or remain unpartnered. The model represents both the availability of potential partners of different types and preferences of individuals for such people. The software estimates preference parameters based on sample survey data on partnerships and population composition. The simulation of matchings and goodness-of-fit are considered. The modeling and theory is in Goyal, Handcock, Jackson, Rendall and Yeung (2023).

Many problems in demography require models for partnership formation that separate latent preferences for partners from the availability of partners. This package consider models for matchings within a bipartite population where individuals have utility for people based on observed and unobserved characteristics. People can form a partnership or remain unpartnered. The models represent both the availability of potential partners of different types and preferences of individuals for such people.

We develop a large-population likelihood framework to estimate preference parameters based on sample survey data on partnerships and population composition. The framework was originally due to Dagsvik (2000) and Menzel (2015). Based on simulation studies conducted in Goyal, Handcock, Jackson, Rendall and Yeung (2023) for realistic population sizes, the model recovers preference parameters that are invariant under different population availabilities. The software uses bootstrap methods to bias correct parameter estimates for small population sizes and produce confidence intervals that have the correct coverage.

The CRAN manual is very detailed. For more information, click here.

The R software package ergm.tapered: Provides a set of terms and functions implementing Tapered exponential-family random graph models (ERGMs). Tapered ERGMs are a modification of ERGMs that reduce the effects of phase transitions, and with properly chosen hyper-parameters, provably removes all multiphase behavior.
Each ERGM has a corresponding Tapered ERGM. Indeed, the ergm.tapered package fits any ergm as it is based on ergm itself.
For more information, click here.

The R software package statnet: software tools for the representation, visualization, analysis and simulation of social network data.

The R software package latentnet: software to fit and evaluate latent position and cluster models for statistical networks.

The R software package networksis: A Package to Simulate Bipartite Graphs with Fixed Marginals through Sequential Importance Sampling.

The R software package ergm: A Package to Fit, Simulate and Diagnose Exponential-Family Models for Networks.

The R software package RDS: that carries out estimation with data collected using Respondent-Driven Sampling. This includes Heckathorn’s RDS-I and RDS-II estimators as well as Gile’s Sequential Sampling estimator. The CRAN manual is very detailed.
For more information, click here.

The R software package sspse: that implements successive sampling population size estimation (SS-PSE). SS-PSE is used to estimate the size of hidden populations using respondent-driven sampling (RDS) data. The package can implement SS-PSE, visibility SS-PSE, and capture-recapture SS-PSE.
The CRAN manual is very detailed.
For more information, click here.

The R software package glmc: Fitting Generalized Linear Models Subject to Constraints.

For more information on R software to implement the statistical methods described in the paper Resource utilization by an avian nest predator: relating resources to a probabilistic measure of animal space use, by John M. Marzluff, J. J. Millspaugh, P. Hurvitz, and Mark S. Handcock, Ecology, 2004, 85:1411-1427, see the Resource Utilization Function Estimation website.

The R software package network: Classes for Relational Data (Carter T. Butts, maintainer).

The R software package ergm.count: Fit, Simulate and Diagnose Exponential-Family Models for Networks with Count Edges (Pavel N. Krivitsky maintainer).

The R software package ergm.userterms: User-specified terms for the statnet suite of packages.

The R software package degreenet: Models for Skewed Count Distributions Relevant to Networks.

The paper: A Framework for the Comparison of Maximum Pseudo Likelihood and Maximum Likelihood Estimation of Exponential Family Random Graph Models by Marijtje A. van Duijn, Krista J. Gile, Mark S. Handcock in Social Networks, Volume 31, Issue 1, 2009, Pages 52-62 presents methodology to enable estimators of Exponential Family Random Graph model parameters to be compared.

We use this methodology to compare the bias, standard errors, coverage rates and efficiency of maximum likelihood and maximum pseudolikelihood estimators. We also propose an improved pseudo-likelihood estimation method aimed at reducing bias. The comparison is performed using simulated social network data based on two versions of an empirically realistic network model, the first representing Lazega’s law firm data and the second a modified version with increased transitivity. The framework considers estimation of both the natural and the mean-value parameters.
The software to reproduce the results in this paper are here.

I have developed statistical models and tools for tracking all-cause mortality and estimating excess mortality. This is to support the COVID-19 pandemic response. These tools are being used by the World Health Organization (WHO). The software has two components: a graphical user interface to the underlying statistical techniques, and the techniques themselves.

Here is the resulting WHO all cause of mortality and excess death calculator.

Using the Shiny framework, I built an application that runs in a web browser and gives the user access to powerful visualization, analysis and modeling of All Cause mortality and Excess Death statistics, without requiring software installation or knowledge of programming in R.

The software is open-source and does not require an internet connection to use. Details are on the github site. Details of the statistical methodology are available here and in the associated publication.