1 of 35

Many quantitative analyses in the social sciences are applied to data regarding characteristics of people, but not to data describing interactions among people. But interactions play an important role in affecting people’s behavior and beliefs that cannot be explained purely in terms of individual attributes or organizational context. In this workshop we will focus on analyzing social network data (who interacts with whom) so that we can relate people's interactions with what they think and do. We draw on statistical concepts that account for the unusual nature of network data as well as substantive theories across the social sciences to specify and interpret social network models.

Topics include models of influence through a social network, choices in a social network, clustering and graphical representations; ethical issues and IRB, and software. Throughout examples are given using simple toy data and analyses in published papers.

Students taking this workshop should have roughly one year of applied statistics so that they are extremely comfortable with the general linear model (regression and ANOVA), and analysis of 2x2 tables.

4

home

reflection

5 of 35

5

home

reflection

6 of 35

6

http://www.nytimes.com/interactive/2013/02/20/movies/among-the-oscar-contenders-a-host-of-connections.html

7 of 35

7

home

reflection

8 of 35

8

Dunbar, R. I. (1998). The social brain hypothesis. brain , 9 (10), 178-190.

9 of 35

Overview

Introduction

Overview
What Are Social Networks?

Representations of Social Networks: Sociomatrix
Representations: Notation
Representations: Sociogram

Characteristics of Social Network Data

Ego Centric Data

Favorites

Barry Wellman on Misconceptions
Doreian: Social Network Effects added to other...
Breiger: Tracking Network Analysis from Metaph...

Mine Frank: Integrating Social Networks into Models and G...
Personal
Two Fundamental Processes Involving Human Social Networks
Selection and Influence
Causality
Scramble Exercise

Influence
Selection
Graphical representations
Centrality
Ethics
Resources

9

home

reflection

10 of 35

Reflection

What part is most confusing to you?

Why?
More than one interpretation?

Talk with one other, share

home

reflection

11 of 35

What Are Social Networks?

A set of actors and the ties (resource flows) or relations (stable states) among them.

close colleagues (relation) among teachers (actors)
help (tie) one teacher (actor) provides to another
communication (tie) between people (actors) in an organization
friendships (relation) among politicians (actors)
links (relation) among web sites (actors)
referrals (tie) among social service agencies (actors)

For me, actors must

have agency
able to take deliberate action
actor network theory ? Can artifacts have agency and take deliberate action?

11

home

reflection

12 of 35

Format of Network Data (W)

12

Your name: Lisa Jones (person 1)

Please indicate who are your closest colleagues at xxx and the frequency with which you interact with each person.

Name Yearly Monthly Weekly Daily

Bob Jones_(2)________ 1 2 3 4

Sue Meyer_(3)________ 1 2 3 4

____________________ 1 2 3 4

Data entered (nominator(i), nominee(i’), frequency)

1 2 2

1 3 4

Your name: Bob Jones (person 2)

Please indicate who are your closest colleagues at xxx and the frequency with which you interact with each person

Name Yearly Monthly Weekly Daily

1. Lisa Jones_(1)________ 1 2 3 4

2. Lin Freeman (4)_______ 1 2 3 4

3. ____________________ 1 2 3 4

4. ____________________ 1 2 3 4

Data entered (nominator(i), nominee(i’), frequency)

2 1 2

2 4 3

Edgelist

home

reflection

13 of 35

13

1 2 3 4 5 6

1|0 1 1 0 0 0

2|1 0 1 0 0 0

3|0 1 0 1 0 1

4|0 0 0 0 1 1

5|0 0 0 1 0 0

6|0 0 1 1 0 0

ROW COLUMN WEIGHT

1 2 1

1 3 1

2 1 1

2 3 1

3 2 1

3 4 1

3 6 1

4 5 1

4 6 1

5 4 1

6 3 1

6 4 1

Nominator Nominee Weight

Sender Receiver Relate

Matrix

Edgelist

Edgelist to Matrix

14 of 35

Representations: Notation

x_ij, takes a value of 1 if i nominates j , 0 otherwise: x_{1 4}=0, x_{1 2}=1
Ken uses:

w_ii’, takes a value of 1 if i nominates i’, 0 otherwise: w_{1 4}=0, w_{1 2}=1

_ii’ represents the fact that it’s the same people, but in different roles, either as sender or receiver

14

home

reflection

15 of 35

Measure of Behavior: Implementation of Innovation in Core Practices

Teacher’s Use of Technology at Time 2 (α=.94)

I use computers to help me...

Never Yearly Monthly Weekly Daily

1 2 | 3 4 5 introduce new material into the curriculum.

1 2 | 3 4 5 guide student communication.

1 2 | 3 4 5 model an idea or activity.

1 2 | 3 4 5 connect the curriculum to real world tasks.

1 2 3 | 4 5 teach the required curriculum.

1 2 3 | 4 5 motivate students.

| indicates mean response

15

Frank, K. A., Zhao, Y., and Borman (2004). Social Capital and the Diffusion of Innovations within Organizations: Application to the Implementation of Computer Technology in Schools." Sociology of Education, 77: 148-171.

Adapt to the new curriculum

16 of 35

Crystalized Sociogram

16

• Each number is a teacher

• Lines connecting two numbers indicate teachers who are close colleagues

• Circles indicate cohesive subgroups

Sequence informed by qualitative

Distance between A

and B reflects history

of school: SES

integration

A

B

D

E

C

Grade 2

Grade 3

Multi grade

Kliqfinder in R

17 of 35

Ripple Plot

17

Overlay talk about technology on social space of crystallized sociogram
Size of node indicates teacher’s use of technology at time 1
Ripples indicate increase in use from time 1 to time 2
Lines indicate talk or help with computers

A

B

D

E

C

Please indicate who has helped you with computers at xxx and the frequency with which you interact with each person

18 of 35

Characteristics of Social Network Data

Directionality

If A takes hostile action against B, B may not take hostile action against A

Valued relations

How frequently does teacher A interact with teacher B?

Multiple relations or ties

Close colleagues (relation)
Help with technology (tie)

Centricity

Sociocentric: whole social network
Egocentric: each person and their own network

Modes

One mode: actor to actor

Friendship, bullying

Two mode: actors and events

Students and the courses they attend
Ceo’s and the boards they are members of

18

home

reflection

19 of 35

Ego Centric Data

19

Wellman, B.A. and Frank, K.A. 2001. "Network Capital in a Multi-Level World: Getting Support from Personal Communities." pages 233-274 in Social Capital: Theory and Research, Nan Lin, Ron Burt and Karen Cook. (Eds.). Chicago: Aldine De Gruyter

home

reflection

20 of 35

20

Two mode: actors

and events

21 of 35

One-Mode Projection vs Two Mode data

Field, S., Frank, K. A., Schiller, K., Riegle-Crumb, C., & Muller, C. (2006). Identifying positions from affiliation networks: Preserving the duality of people and events. Social networks , 28 (2), 97-123.

W

W’W

WW’

22 of 35

Reflection

Think: Identify a network of interest

Who are the actors
What are the relations or ties?

Directionality
Valued relations
Multiple relations

Modality
Centricity

[make some notes, you’ll need them in a few minutes]

22

home

reflection

23 of 35

Favorites:�Barry Wellman on Misconceptions

23

24 of 35

Mine�Frank: Integrating Social Networks into Models and Graphical Representations

Multilevel models

Accounts for nesting of people within groups (e.g., students within schools)

Effects of groups modeled at the group level (e.g., effect of school restructuring on achievement
Assumptions

Groups independent of each other
People within groups independent of each other. Hmmmmmmmm.

People within schools influence each other

Student to student
Teacher to teacher
Teacher to student

People within schools select interaction partners

Adolescents’ friends and peers
Teachers’ close colleagues
Back to multilevel models, one of the best ways to control for dependencies

Frank, K. A. (1998). Chapter 5: Quantitative methods for studying social context in multilevels and through interpersonal relations. Review of research in education, 23(1), 171-216.

24

home

reflection

25 of 35

Social Processes in Schools

25

26 of 35

Theoretical Model for Curricular Innovation with Networks

26

Curriculum

Teachers’ practice

Student engagement

Student learning

Professional

development

Teacher network

Student network

27 of 35

Studying the Racial Discipline Gap

27

28 of 35

Two Fundamental Processes Involving Human Social Networks �

Influence: Change in actors’ beliefs or behaviors as a result of interaction with others

Teachers’ change uses of computers as a result of use of others’ around them (Frank, Zhao and Borman 2004)
Adolescents’ change effort in school in response to peers’ effort (Frank et al 2008, AJS; )

Selection: Actors choose with whom to interact as a function of the characteristics of the chooser, chosen, and the dyad

Teachers choose to help others with technology based on close collegial ties (Frank and Zhao 2005)
French bankers choose whom to take supportive or hostile action against based on friendship structure (Frank and Yasumoto, 1998)
Who does one child nominate as a bully?

Each process relates social network to beliefs or behaviors

28

Frank, K.A., & Fahrbach, K. 1999. "Organizational Culture as a Complex System: balance and Information in Models of Influence and Selection." Special issue of Organization Science on Chaos and Complexity, Vol 10, No. 3, pp. 253-277..

See notes for other papers

home

reflection

29 of 35

Exposure: Graphical Representation

29

Y_i’t-1

W_{ii’t-1🡪t}

Y_it

t

t-1

B

C

D

30 of 35

Selection of Network Partners: Graphical Representation

30

t

t-1

W_{ii’t-1🡪t}

C

B

C

D

31 of 35

Selection and Influence

Selection and Influence always present

Ignore them at your peril! – biased / wrong estimates

31

Influence

selection

0 1 2 3

Time

Change in Behavior

Change in Relations

Behavior |

Relations |

Leenders, R. (1995). Structure and influence: Statistical models for the dynamics of actor attributes, network structure and their interdependence. Amsterdam: Thesis Publishers.

home

reflection

32 of 35

Causality

Is it selection or influence?

Do people choose to interact with others like themselves (selection) or do they change

Birds of a feather flock together

Beliefs/behaviors based on interactions with others (influence)?

She’s hanging out with the wrong crowd!

Need longitudinal data!!!!!!!

Influence

With whom did you talk over the last week: asked at week 2 (1🡪2)
What are your beliefs? (asked at week 1)
What are your beliefs (asked at week 2)

Selection

With whom did you talk over the last week: asked at week 1 (0🡪 1)
With whom did you talk over the last week: asked at week 2 (1🡪 2)
What are your beliefs? (asked at week 1, or asked at weeks 1 and 2 and take the average)

32

home

reflection

33 of 35

Scramble Exercise: Become the Social Engine

Form: Meet and share in groups of 3-4
Scramble: Form new group of 3-4 people
Matchmaker: I will introduce 2 people who have a common interest

Each of the 2 will introduce 2 others
And so on … (if you were introduced to someone you are now the matchmaker -- make an introduction)
Enter your introductions in chat

33

home

reflection

34 of 35

DEBRIEF

Were you influenced?

How, why?

How did you choose with whom to interact?

First time?
Second time?

34

home

reflection

35 of 35

35