It’s the sum of degrees of one’s friends. For example, look at Jennie in this picture

?

Her friends are Pat, Pam and Ann. Pat has 4 friends, Pam has 5 and Ann has 3. The sum is 12, which is Jennie’s “2-local eigenvector” score.

?

steve

?

The Gatton College of Business and Economics’ Department of Management invites applications for a one-year postdoctoral position in the area of social network analysis and network science, with a focus on scientific collaboration and team science.

This is a position involving research between the University of Kentucky’s (UK) LINKS Center for Social Network Analysis, the UK Center for Clinical and Translational Science (CCTS), and the University of Florida. The candidate will be an active participant in the LINKS Center, the preeminent center for the study of social networks in organizations, which is housed in the Department of Management. The LINKS Center hosts an annual workshop on network methods and analysis, a biennial small conference that attracts many of the top faculty in social network analysis from around the world, and an active seminar series. More information about the LINKS Center can be found at . The UK Center for Clinical and Translational Science () unites clinicians, researchers, and communities through innovative team science to accelerate the translation of basic science discoveries to tangible improvements in health.

The ideal candidate should have expertise in social network analysis, network science, and data science (including familiarity with R, Python and databases), and an interest in the study of science and scientific collaboration. Familiarity with Natural Language Processing will be considered a plus. The candidate should hold a Ph.D. in a related area, although exceptional Ph.D. candidates at the ABD stage might also be considered.

The position will open immediately and cover a one-year term; a renewal is possible pending funding renewal. To apply, interested applicants should apply online at: .

Applications must include the following: a cover letter detailing your expertise and research interests (upload under Specific Request 1), an academic transcript, and a curriculum vitae. You will be asked to provide the names and contact information for at least two references when prompted in the application (upload under Specific Request 2). This information will be utilized to solicit recommendation letters from your references within the employment system.? Applications will be received until the position is filled.

Over the last 95 years, UK’s Gatton College of Business and Economics has been preparing principled leaders for the global economy, producing high quality, influential research, and supporting economic growth in Kentucky and beyond. Accredited by the AACSB, Gatton proudly offers a full range of undergraduate, graduate and professional business and economics degrees and certificates. We are housed in a recently renovated 220,000 square foot state-of-the-art facility where the college accommodates the fastest growing enrollment on UK’s campus, expected to reach over 4,000 Students by fall of 2019. Through teaching, research, and outreach, the Gatton College has a direct, tangible influence on the lives of Kentucky’s citizens and people around the world. We are looking for professionals who embody the College’s tagline of “Blue Means Business”. Please consider joining our team.

The University of Kentucky is committed to a diverse and inclusive workforce by ensuring all our students, faculty, and staff work in an environment of openness and acceptance. We strive to foster a community where people of all backgrounds, identities, and perspectives can feel secure and welcome. We also value the well-being of each of our employees and are dedicated to creating a healthy place to work, learn and live. In the interest of maintaining a safe and healthy environment for our students, employees, patients and visitors the University of Kentucky is a Tobacco & Drug Free campus. As an Equal Opportunity Employer, we strongly encourage veterans, individuals with disabilities, women, and all minorities to consider our employment opportunities.

steve

Please join Statistical Horizons in Philadelphia for a 2-day seminar...

Introduction to Social Network Analysis
Taught by Dr. Stephen Borgatti
May 3-4, 2019, Philadelphia

This 2-day intensive workshop provides an introduction to doing research on social networks. The course is very hands-on, emphasizing mastering the software and using the concepts and methods to answer research questions. We will use the UCINET software package.

Register before April 3 to receive early registration pricing.

?

?

Contact us at?info@....?

?

?

Stephen P. Borgatti

Paul Chellgren Endowed Chair and Professor

Dept. of Management

Gatton College of Business and Economics

University of Kentucky

steve.borgatti@...

?

Jordan, can you send me the data (steve.borgatti@...)?

?

steve

?

Dear group,

?

Sorry to disturb your weekend.

?

I’m having a spot of bother with centrality scores and was wondering if anyone has a solution or work around.

?

Data: Valued 1 mode (4028 x 4028) created from a 2 mode network (4028 x 100).

?

Problem: I am unable to generate centrality scores for 1 mode networks - this includes the multiple measures function, single measures, and the legacy Degree centrality option. ?UCInet either times out or simply doesn’t produce the scores

?

The 2 mode centrality function works fine and there are no issues with other functions for 1 mode networks (e.g. cohesion). I have worked with similar sized networks in the past and have never had this issue. UCinet is up to date

?

Any help would be greatly appreciated.

?

Best wishes,

?

Jordan

?

Dr. Jordan Soukias Tchilingirian
Lecturer
Department of Social and Policy Sciences
University of Bath
Office: 3 East 4.14
Phone: +44(0)125 386861

?

It might be clearer to say that, across 10,000 random assignments of persons to groups, the probability of observing a difference as large as 29.756 is exceedingly low – less than .001. But yes, group 2 members have many more ties (or higher strengths of tie), on average, than do members of group 1. Of course, group 2 seems like a very select group, just 31 members against 769 in the other group.

?

?

Jen, try

?

->dsp centdiff(padgm padgb undir)

?

As for densitydiff, as I explained before, your version of the program is calculating things correctly but is printing the wrong label: in the output, it is using the word centralization instead of density. This has been corrected, but you would have to download the current version to see it.

?

steve

?

Jen, first, you’re right: it’s mislabeled. But it is doing density. As for the numbers, is it possible your data are valued? If so, the program will use average tie strength. If your hand-calculating was based on dichotomized data, you would get different answers. You could do

?

->d1 = dichot(network1rows)

->d2 = dichot(network2rows)

->dsp densitydiff(d1 d2 undir)

?

steve

?

Dear UCInet user group,

?

Although I use netdraw regularly, I’m looking at some alternate data vis packages that are compatible with UCINet.

They often want DL files.

Looking at the UCInet help I have followed the below, after which the program (UCINET 6) crashes every time – even with small networks.

?

Procedure undertaken:

UCINET>Data>Export>DL (Screen shot follows)

?

As soon as press ok the system crashes L

Just wondering if others have had this issues, is there a work around, or is it ….user error? ;)

?

Thank you for your consideration and sending best wishes,

Bec

?

Hi Steve,

Thank you so much, this is really helpful.

Best wishes,

Bec

?

?

Hi Rebecca, the help files are little behind. A quick description can be found here:

?

?

steve

?

?

?