***** To join INSNA, visit http://www.insna.org ***** Hi Joanna, Based on your description, I assume you want to collect egocentric network data from a sample of individuals who do NOT necessarily belong to the same group (ie you don't have a roster of completed network). If this is the case, then before you try any one of the tools that Eric has listed, I'd suggest the following: (1) think about how you are going to compare the egocentric network of respondents and what statistics/measures you want to use for comparison, and more importantly, (2) think about the survey instrument/network generator(s) that you plan to use and whether it/they can obtain enough alters for you to construct the network and calculate the statistics. These are the crucial methodological questions to think through at the initial stage of research design. For example, you can use the 'important matter' name generator to collect data, but if you can only obtain a handful of alters from most respondents, then you won't have enough variation for most network statistics. Imagine if most respondents report about 1 to 5 close friends, you may, at best, compare the composition of ego network (proportion of gender, racial and ethnicity etc.). But you may not have enough variation in the observed structural measures (size, density...). The Online first section and the latest issue of Social Networks (Jan 2015) have a few articles on the issues with egocentric network and core discussion network (the egocentric network elicited by the GSS name generator). You should have access to the full text of all these articles via your school's subscription. By David Eagle and Rae Jean Proeschold-Bell: Methodological considerations in the use of name generators and interpreters By Mario Luis Small, Vontrese Deeds Pamphile, Peter McMahan: How stable is the core discussion network? By Matthew E. Brashears and Eric Quintane: The microstructures of network recall: How social networks are encoded and represented in human memory You can check out my article for a compact but comprehensive review on the literature regarding egocentric network generators (other than these latest ones). Check the phone book: Testing information and communication technology (ICT) recall aids for personal network surveys Also check out the work by Cuihua Shen and Wenhong Chen in the latest issue if your study context involves new technologies. Hope these helps. Patrick Yuli Patrick Hsieh, Ph.D. Survey Methodologist/Digital Sociologist Program on Digital Technology & Society Survey Research Division RTI International 230 W Monroe St, Chicago, IL 60606 (312)777-5234 http://www.yulipatrickhsieh.org/ http://twitter.com/coolpat http://www.egogalaxy.org/ On Tue, 6 Jan 2015 02:25:46 +0000, Jones, Eric C <[log in to unmask]> wrote: >***** To join INSNA, visit http://www.insna.org ***** > >Hi Joanna, > >the following two programs are good for survey authoring, collecting, analyzing and visualizing data. they are quite similar but have a few different features, both originally developed by Chris McCarty. > >http://sourceforge.net/projects/egonet/ (free, Java version, can also create whole networks out of personal networks) >http://socioworks.com/productsall/egonet/ (commercial version by mdlogix, has pretty nice graphics) > >E-Net may also serve you well for analysis (doesn't author/collect data), as it has some additional algorithms for analysis plus similar data mining/filtering to the mdlogix egonet. https://sites.google.com/site/enetsoftware1/ > >David Kennedy at Rand is developing EgoWeb for tablets/mobile devices, and Jose Luis Molinas at University of Barcelona is developing another type of EgoNet mobile. check with them if you just need data collection. C-IKNOW i think is now out of production, but was nice for authoring and data collection online. SocioWorks (http://socioworks.com/productsall/socioworks/) will collect network data in online surveys for download. > >a good resource is McCarty's 2002 article in Journal of Social Structure. http://www.cmu.edu/joss/content/articles/volume3/McCarty.html. McCarty and colleagues also found that taking random subsamples from larger networks (under specified conditions) gave accurate portrayals of network structure, so that you don't have to burden ego so much with the (N*N-N)/2 set of alter-alter ties. http://www.bebr.ufl.edu/sites/default/files/Impact%20of%20Methods%20for%20Reducing%20Respondent%20Burden_0.pdf > >there are now quite a few people studying personal networks, so hopefully you'll get some more responses from the list for reading and software. > >eric > > >________________________________ >From: Social Networks Discussion Forum [[log in to unmask]] on behalf of Joanna Weill [[log in to unmask]] >Sent: Monday, January 05, 2015 18:11 >To: [log in to unmask] >Subject: [SOCNET] Egocentric Network Comparisons > >***** To join INSNA, visit http://www.insna.org ***** >Hi everyone, > >I am designing a study where I will be collecting egocentric network information from individuals and hopefully comparing these networks. I know there are some statistical problems with doing this, but I have also been told that there may be some people on this listserv who have some good suggestions and resources for dealing with these problems. If anyone has any readings they could direct me to, I would really appreciate it--preferably readings that are accessible to someone who is a relative beginner on social network analysis. > >Thanks in advance for any advice you may have. > >- Joanna Weill > >-- >Joanna M. Weill >Ph.D. Candidate, Department of Psychology >University of California, Santa Cruz >[log in to unmask] >Chair, Graduate Student Committee, Society for the Psychological Study of Social Issues (APA Div. 9) _____________________________________________________________________ SOCNET is a service of INSNA, the professional association for social network researchers (http://www.insna.org). To unsubscribe, send an email message to [log in to unmask] containing the line UNSUBSCRIBE SOCNET in the body of the message.