In this pilot project, the investigators created oncologist-oncologist networks based on shared patients using data from the National Cancer Institute (NCI)’s Surveillance, Epidemiology, and End-Results (SEER)-Medicare program. To do this, they identified 8,924 elderly Medicare patients who were diagnosed with stage IV colorectal cancer (CRC) in one of 15 geographically distinct regions of the United States between 1993-2007 and received at least one of six specific chemotherapy agents in the year following diagnosis.
Logistically, this study aimed to develop a novel network survey method in the resource-limited setting of Uganda, in order to accurately measure several types of social network interactions (known as “multiplexity” in social network parlance) using a photographic database of participants. Scientifically, this study aimed to assess how network structure and composition are associated with several health traits, behaviors and attitudes, as well as with other economic and development outcomes.
This study aimed to assess the potential of social network-based targeting to improve the dissemination of public health interventions. In 32 villages in rural Honduras, we conducted a randomized controlled trial of network-based public health interventions: chlorine for water purification and multivitamins for micronutrient deficiencies. In one third of the villages chosen at random, interventions were introduced to a 5% random sample of villagers.
The goal of this project was to develop and test a survey to measure referral partners and information exchange partners within a sample of primary care and specialist physicians. To accomplish this, the study team examined the relationship between a measure of the number of shared Medicare patients between two physicians (ascertained using Medicare claims data) and the presence of a referral or information exchange relationship (reported by physicians).
This pilot project entailed the development of a new social network data collection software tool called Netriks. The new version of the tool was successfully completed and is capable of capturing entire social networks among all kinds of populations, including those that may not be used to formal questionnaires (e.g., traditional, pre-literate societies) or who may be better able to use a picture-based method of network identification (e.g., low-literate populations, school children, elderly nursing home residents with mild dementia, etc.).
The Department of Biostatistics and the MacMillan-CSAP Workshop on Quantitative Research Methods are pleased to announce a seminar given by Mark Handcock, Professor of Statistics at the University of California Los Angeles.
“Exponential-family Approaches to Jointly Model Network Relations and Endogenous Attributes”
The Department of Biostatistics and the MacMillan-CSAP Workshop on Quantitative Research Methods are pleased to announce a seminar given by Mark Handcock, Professor of Statistics at the University of California Los Angeles.
“Estimating Hidden Population Size Using Respondent-Driven Sampling Data”
“Using Social Networks for Good” is the topic of the next In the Company of Scholars talk at the Graduate School of Arts and Sciences.
The featured speaker will be Dr. Nicholas A. Christakis, the Sol Goldman Family Professor of Social and Natural Science. The talk will take place at 4 p.m. on Wednesday, Feb. 11 in Rm. 119 of the Hall of Graduate Studies, 320 York St. A reception will follow. The Yale community is invited.