| Member Profile : Philippa Pattison |
|
 | Contact Information | Address: -Map Me-
Philippa Pattison
University of Melbourne, Department of Psychology
PVC (Learning & Teaching)
106, Old Geology Building
Parkville, Victoria, Australia 3010
Phone : +61 3 8344 4014
Fax : +61 3 9347 6618
E-mail : pepatt@unimelb.edu.au
Website : http://www.psych.unimelb.edu.au/people/staff/PattisonP.html
|
| Bibliographic Information |
|
| | | Software & Data | | Active Calendar Listings |
|
|
|
| | | Network Graduate Programs | | Network Courses |
|
|
|
| | | Jobs Posted | | Sunbelt Submissions |
|
| Sunbelt XXIX - March 10 to March 15, 2009 - Bahia Hotel | | Abstract : Algebraic foundations for dynamic relational structures |
In this paper, we discuss the algebraic underpinnings of dynamic relational structures. Building on Moody’s (2002) concept of a time-ordered path, we describe several different composition rules for dynamic relational observations, as well as the relational interval algebras to which various compositional forms give rise. We discuss the implications of these ideas for the measurement and modeling of dynamic relational systems.
Reference: Moody, J. (2002). The importance of relationship timing for diffusion. Social Forces, 81, 25-56. |
| Sunbelt XXX - June 29 to July 04, 2010 - Riva del Garda Fierecongressi | | Abstract : Conditional estimation of exponential random graph models from snowball samples |
| Obtaining survey network data in a large population in order to understand the structure of the network may be prohibitively difficult and costly and it is therefore often of interest to estimate models for networks using data from various network sampling designs, such as link-tracing designs. We focus here on the case of snowball sampling designs, designs in which an initial sample of network members are asked to nominate their network partners, their network partners are then traced and asked to nominate their network partners, and so on. We assume an exponential random graph model (ERGM) of a particular parametric form and outline a conditional maximum likelihood estimation procedure for obtaining estimates of ERGM parameters. This procedure is intended to complement the likelihood approach developed by Handcock and Gile (in press) by providing a practical means of estimation when the size of the complete network is unknown and/or the complete network is very large. A main difference in our conditional procedure compared to the full maximum likelihood procedure is that it requires only simulation of alternative outcomes of observed tie variables, not of unobserved ones. We report the outcome of a simulation study with a known model designed to assess the impact of initial sample size and population size on properties of the estimates. We also present an illustrative application for a large network and conclude with a discussion of further developments of the approach. |
| Sunbelt XXVI - April 25 to April 30, 2006 - Vancouver | | Workshop : 4a. The methodology of ERG (p*) models and an introduction to new model specifications |
|
| Workshop : Both 4a and 4b : The methodology of ERG (p*) models and an introduction to new model specifications |
|
|
|
| |
|
