Skip to content
Archive of posts filed under the Network Theory category.

New paper describing innovations to the classical Network Scale-up Method for determining population size estimates

“Improving the Network Scale-Up Estimator: Incorporating Means of Sums, Recursive Back Estimation, and Sampling Weights.” PLoSOne 10(12): e0143406.
Patrick Habecker, Kirk Dombrowski, and Bilal Khan

Researchers interested in studying populations that are difficult to reach through traditional survey methods can now draw on a range of methods to access these populations. Yet many of these methods are more expensive and difficult to implement than studies using conventional sampling frames and trusted sampling methods. The network scale-up method (NSUM) provides a middle ground for researchers who wish to estimate the size of a hidden population, but lack the resources to conduct a more specialized hidden population study. Through this method it is possible to generate population estimates for a wide variety of groups that are perhaps unwilling to self-identify as such (for example, users of illegal drugs or other stigmatized populations) via traditional survey tools such as telephone or mail surveys—by asking a representative sample to estimate the number of people they know who are members of such a “hidden” subpopulation. The original estimator is formulated to minimize the weight a single scaling variable can exert upon the estimates. We argue that this introduces hidden and difficult to predict biases, and instead propose a series of methodological advances on the traditional scale-up estimation procedure, including a new estimator. Additionally, we formalize the incorporation of sample weights into the network scale-up estimation process, and propose a recursive process of back estimation “trimming” to identify and remove poorly performing predictors from the estimation process. To demonstrate these suggestions we use data from a network scale-up mail survey conducted in Nebraska during 2014. We find that using the new estimator and recursive trimming process provides more accurate estimates, especially when used in conjunction with sampling weights.


Paper on Bateson’s Rule to appear in Complex Adaptive Systems 2014

Towards a Formal Understanding of Bateson’s Rule:
Chromatic Symmetry in Cyclic Boolean Networks and its Relationship to Organism Growth and Cell Differentiation

Yuri Cantor – CUNY Graduate Center, Doctoral Program in Computer Science
Bilal Khan – CUNY Graduate Center, John Jay College Department of Mathematics and Computer Science
Kirk Dombrowski – Department of Sociology, University of Nebraska – Lincoln

There has been considerable prior research on the biological processes of morphogenesis and cellular differentiation, and the manner by which these processes give rise to symmetries in biological structures. Here we extend our previous work on thermal robustness and attractor density in cyclic formal Boolean dynamical systems, introducing a new form of spectral analysis on digital organisms at the cellular level. We interpret the phenomena of radial and bilateral symmetry in terms of spatial periodicities in the color sequences, as manifested by an organism while it orbits in its attractors. We provide new results on the influence of various organism properties on its emergent color symmetries—providing initial insights toward an eventual formal understanding of metamerism and Bateson’s Rule.

Full paper is available here: CAS2014

New Publication on Methamphetamine Using Populations in New York City

Estimating the Size of the Methamphetamine-Using Population in New York City Using Network Sampling Techniques

Kirk Dombrowski, Bilal Khan, Travis Wendel, Katherine McLean, Evan Misshula, and Ric Curtis

As part of a recent study of the dynamics of the retail market for methamphetamine use in New York City, we used network sampling methods to estimate the size of the total networked population. This process involved sampling from respondents’ list of co-use contacts, which in turn became the basis for cap-ture-recapture estimation. Recapture sampling was based on links to other respondents derived from demographic and “telefunken” matching procedures–the latter being an anonymized version of telephone number matching. This paper describes the matching process used to discover the links between the solic-ited contacts and project respondents, the capture-recapture calculation, the estimation of “false matches”, and the development of confidence intervals for the final population estimates. A final population of 12,229 was estimated, with a range of 8,235 – 23,750. The techniques described here have the special vir-tue of deriving an estimate for a hidden population while retaining respondent anonymity and the ano-nymity of network alters, but likely require larger sample size than the 132 persons interviewed to attain acceptable confidence levels for the estimate.

Keywords: Population Estimation; Network Methods; Methamphetamine; Anonymous Sampling

Dombrowski, K. , Khan, B. , Wendel, T. , McLean, K. , Misshula, E. & Curtis, R. (2012). Estimating the Size of the Methamphetamine-Using Population in New York City Using Network Sampling Techniques. Advances in Applied Sociology, 2, 245-252. doi: 10.4236/aasoci.2012.24032.

New Publication: Advances in Anthropology

Assessing Respondent Driven Sampling for Network Studies in Ethnographic Contexts

Kirk Dombrowski, Bilal Khan, Joshua Moses, Emily Channell, and Evan Misshula

Respondent Driven Sampling (RDS) is generally considered a methodology for recruiting “hard-to-reach” populations for social science research. More recently, Wejnert has argued that RDS analysis can be used for general social network analysis as well (where he labels it, RDS-SN). In this article, we assess the value of Wejnert’s RDS-SN for use in more traditional ethnographic contexts. We employed RDS as part of a larger social network research project to recruit n = 330 community residents (over 17 years of age) in Nain, a predominantly (92%) aboriginal community in northern Labrador, Canada, for social network interviews about food sharing, housing, public health, and community traditions. The peer referral chains resulted in a sample that was then analyzed for its representativeness by two means—a comparison with the Statistics Canada 2006 Census of the same community, and with house-by-house demographic sur- veys carried out in the community as part of our research. The results show a close fit with available community statistics and our own survey. As such, we argue that the RDS sampling used in Nain was able to provide a useful and near-representative sample of the community. To demonstrate the usefulness of the results, the referral chains are also analyzed here for patterns in intragroup and intergroup relation- ships that were apparent only in the aggregate.

Keywords: Respondent Driven Sampling; Labrador Inuit; Ethnographic Methods; Network Sampling; Arctic Social Science

Recent RO1 Grant Submission: Addressing HCV-related hepatocellular carcinoma: the current and future epidemics

PI: Holly Hagan (NYU)
Investigators: Bilal Khan and Kirk Dombrowski

Hepatitis C virus (HCV)-related deaths now exceed HIV-related deaths in the US. Throughout the world, HCV is hyperendemic in people who inject drugs (PWID). New outbreaks of acute HCV infection are unfolding in HIV-positive men who have sex with men (MSM) and in 15-24 year olds who have transitioned from abuse of prescription opioids to illicit opiate injection. In patients with chronic HCV infection, 20-25% will develop liver disease which may manifest as cirrhosis, liver failure or hepatocellular carcinoma (HCC). The prognosis for HCC is extremely poor, and HCV is the chief etiologic agent for this type of cancer. Recent discoveries in HCV prevention and treatment provide a great opportunity to reverse the trend toward increasing rates of HCV, HCV/HIV co-infection, and HCC. This study will use the methods of Implementation Science – research synthesis, mathematical modeling and simulation, and comparative effectiveness analyses – to determine how best to constitute a portfolio of interventions for the prevention and control of HCV and its consequences while taking into account limited resources and underlying epidemiologic and social network features. A dissemination plan will make extensive use of technology, including social media, and guidance from key stakeholders. These are our specific aims:
1. Synthesize evidence characterizing a) transition from misuse of prescription opioids to drug injection, b) HCV epidemiology and prevention for PWID and HIV+ MSM, and c) progression and treatment of HCV disease in these two groups, to derive best estimates to populate our HCV natural history and transmission models.
2. Use agent-based modeling to estimate the effects of scale-up of individual and combined prevention- and treatment-related interventions on HCV transmission and natural history in PWID and HIV+MSM.
3. Determine the combination of interventions for particular budget and epidemiologic scenarios that a) minimizes acute and chronic HCV infections, including HIV/HCV co-infection, b) prevents the greatest number of cases of HCV-related HCC and other serious sequelae, c) maximizes life expectancy and quality-adjusted life expectancy and d) reduces health disparities.
4. In collaboration with our Dissemination Advisory Board, apply an integrated knowledge-exchange approach to providing our target audiences (policymakers, public health and harm reduction practice communities, PWID and HIV+MSM) with the knowledge and tools to implement evidence-based HCV control strategies or reduce personal risk of infection and its consequences.
The broad objective of this study is to provide an evidence base to guide allocation of scarce public resources in the US and other countries where HCV is principally transmitted among PWID. This will be accomplished by synthesizing, modeling and translating very recent developments in HCV epidemiology, prevention and treatment into practical tools to optimize population health.