Andrew C. Thomas's research while affiliated with Carnegie Mellon University and other places

Publications (11)

Conference Paper
In popular online social networks, there are various kinds of user behavior (e.g. retweeting, posting hashtags on Twitter; wall-posting, commenting on Facebook). At the same time there exist different kinds of relationships among users (e.g. follow relationship or mention relationship in Twitter). It is interesting to study how these relationships...
Article
Full-text available
Intervention studies in school systems are sometimes aimed not at changing curriculum or classroom technique, but rather at changing the way that teachers, teaching coaches, and administrators in schools work with one another—in short, changing the professional social networks of educators. Current methods of social network analysis are ill-suited...
Article
Full-text available
The rise of socially targeted marketing suggests that decisions made by consumers can be predicted not only from their personal tastes and characteristics, but also from the decisions of people who are close to them in their networks. One obstacle to consider is that there may be several different measures for "closeness" that are appropriate, eith...
Article
Full-text available
The rise of socially targeted marketing suggests that decisions made by consumers can be predicted not only from their personal tastes and characteristics, but also from the decisions of people who are close to them in their networks. One obstacle to consider is that there may be several different measures for "closeness" that are appropriate, eith...
Article
Full-text available
This study is an effort to inventory and review the assessment methodologies and generate consistent assumptions across a wide range of data for estimating the geologic resource for storing CO 2 in the underground, following with an example of storage resource calculations for the Oriskany sandstone. Results of comparative analysis indicate that th...
Article
Discussion of "Network routing in a dynamic environment" by N.D. Singpurwalla [arXiv:1107.4852]
Article
The authors consider processes on social networks that can potentially involve three factors: homophily, or the formation of social ties due to matching individual traits; social contagion, also known as social influence; and the causal effect of an individual's covariates on his or her behavior or other measurable responses. The authors show that...
Article
With the decennial redistricting cycle starting anew in 2011, there is an opportunity to learn from the lessons of the past cycle as legislators draw their own boundaries in most states, and independent commissions draw them in the others. While the use of commissions has been trumpeted as a way of improving electoral systems, there has been little...
Article
The deployment of improvised explosive devices (IEDs) along major roadways has been a favoured strategy of insurgents in recent war zones, both for the ability to cause damage to targets along roadways at minimal cost, but also as a means of controlling the flow of traffic and causing additional expense to opposing forces. Among other related appro...
Article
Full-text available
Many researchers believe that consumers' decisions are not only decided by their personal tastes, but also by the decisions of people who are in their networks. On the other hand, social scientists are more interested in consumers' dichotomous choice. So an auto-probit model accommodating multiple networks are very useful. However, Current methods...

Citations

... ODA commitments and disbursement data collected from 1960. However, there were insufficient/missing observations of 24 According to Fienberg & Thomas (2011), "A network is a representation for a collection of individuals or other units connected in a pairwise fashion by relationships, such as friendship. Networks are typically displayed visually as "graphs," so that individuals correspond to the "nodes" of a graph, with the existence of a relationship indicated by an edge between pairs of nodes." ...
... These communication links are based on users @mentioning each other and result in communities that are more interactive, especially about the common interest. As pointed out in [31], @mention links are a stronger measure of interaction activity, compared to follower/following links. Due to this different usage of links, the communities detected by the CICD and HICD methods may overlap but are unlikely to be a subset of one another (as users may @mention each other even when they are not topologically connected). ...
... They have been developed under various settings, including undirected graphical models for cross-sectional data (Epskamp, Waldorp, et al., 2018;Burger et al., 2022), directed networks for longitudinal data (Gile & Handcock, 2017;Borsboom et al., 2021;Ryan et al., 2022), and extended networks with latent variables for time-series data or panel data (Epskamp, 2020). These methods have received wide applications in education (Sweet et al., 2013;Willcox & Huang, 2017;Koponen et al., 2019;Siew, 2020;Simon de Blas et al., 2021), psychology (Burgess & Hitch, 1999;Van Der Maas et al., 2017;Fried et al., 2017;Epskamp, Borsboom, & Fried, 2018;Borsboom et al., 2021), and health sciences (Luke & Harris, 2007;Brunson & Laubenbacher, 2018;Mkhitaryan et al., 2019;Kohler et al., 2022). ...
... indirect (e.g., the effect of interactions between my friends and their neighbors on myself) networking processes (Leenders 2002;Pinkse and Slade 2010;Zhang et al. 2013). ...
... We asked this question because these two different, yet related, social processes may require different interventions to address their impact on postdisaster mental health outcomes. Shalizi and Thomas (2011) argued and demonstrated that direct social influence effects cannot be nonparametrically isolated from observational data, in part due to the generic confounding of homophily and social influence. Consequently, we did not attempt to give specific weights to the contributions of homophily versus social influence for any autocorrelation of PTSS found in the network. ...
... Rather than a decision-theoretic treatment, we consider a method based in part on social network analytical methods, namely, that the deployment pattern of IEDs induces a subgraph on a full road network, and that the deployment on any given road is unknown to anyone traversing the graph until arriving there, though there may be prior information on the likelihood of a deployment. The full treatment, as acknowledged in Singpurwalla, is illustrated by Thomas and Fienberg (2011); here, we give a brief overview of our method and how it compares with Singpurwalla's approach. 2. Canadian traveler problems and network transition times. ...