Local Networks

1
Local Networks

• Overview
• Personal Relations
• Core Discussion Networks
• To Dwell Among Friends
• Questions to answer with local network data
• Mixing
• Local Context
• Social Support
• Strategies for Analysis
• Content
• Structure
• Software
• UCINET PAJEK

2
Local Networks
Core Discussion networks
Question asked From time to time, most people
discuss important matters with other people.
Looking back over the last six months -- who are
the people with whom you discussed matters
important to you? Just tell me their first names
or initials.

• Why this question?
• Only time for one question
• Normative pressure and influence likely travels
  through strong ties
• Similar to best friend or other strong tie
  generators

3
Local Networks
Types of measures Network Range the extent to
which a persons ties connects them to a diverse
set of other actors.
Includes Size, density, homogeneity
Network Composition The types of alters in egos
networks. Can include many things, here it is
about kin.
4
Local Networks
Distribution of total network size, GSS 1985
Percent
5
Local Networks
Network size by
Age Drops with age at an increasing rate.
Elderly have few close ties. Education Increase
s with education. College degree 1.8 times
larger Sex (Female) No gender differences on
network size. Race African Americans networks
are smaller (2.25) than White Networks (3.1).
6
Local Networks
Proportion Kin, GSS 1985
7
Local Networks
Proportion Kin by
Age
8
Local Networks
Proportion Kin by
Education Proportion decreases with education,
but they nominate more of both kin and non-kin in
absolute numbers. Sex (Female) Females name
slightly more kin than males do. Race African
American cite fewer kin (absolute and proportion)
than do Whites.
9
Local Networks
Network Density
Recall that density is the average value of the
relation among all pairs of ties. Here, density
is only calculated over the alters in the network.
D0.5
10
Local Networks
Density
11
Local Networks
Network Density
Age Increases as we age. Education Decreases
among the most educated. Race No differences
by race. Size of Place People from large
cities have lower density than do those in small
cities.
12
Local Networks
Network Heterogeneity
Heterogeneity is the variance in type of people
in your network.

• Networks tend to be more homogeneous than the
  population. Marsden reports differences by Age,
  Education, Race and Gender. He finds that
• Age distribution is fairly wide, almost evenly
  distributed, though lower than the population at
  large
• Homogenous by education (30 differ by less than
  a year, on average)
• Very homogeneous with respect to race (96 are
  single race)
• Heterogeneous with respect to gender

13
Local Networks
Network Heterogeneity
Heterogeneity differs by
Age Tends to decrease as we age Education Het
erogeneity increases with education Race No
differences in age. Minorities tend to have
higher race-heterogeneity (consistent with Blaus
intergroup mixing model) and lower gender
heterogeneity. Size of place Large settings
tend to be correlated with greater heterogeneity
in the network.
14
Local Networks
Fischers Work.
What does Fischer have to say about Homogeneity
in local nets?
15
Local Networks
Questions that you can ask / answer
Mixing The extent to which one type of person
is tied to another type of person (race by race,
etc.) Aspects of the local context Peer
delinquency Cultural milieu Opportunities Socia
l Support Extent of resources (and risks)
present in a type of network environment. Structu
ral context (next class)
16
Local Networks
Calculating local network information.
1) From data, such as the GSS, which has
ego-reported information on alter 2) From global
network data, such as Add Health, where you have
self-reports on alters behaviors.
17
Local Networks
Calculating local network information 1 GSS
style data.
This is the easiest situation. Here you have a
separate variable for each alter characteristic,
and you can construct density items by summing
over the relevant variables. You would, for
example, have variables on age of each alter such
as Age_alt1 age_alt2 age_alt3 age_alt4
age_alt5 15 35 20 12 . You get the
mean age, then, with a statement such
as meanagemean(Age_alt1, age_alt2, age_alt3,
age_alt4, age_alt5) Be sure you know how the
program you use (SAS, SPSS) deals with missing
data.
18
Local Networks
Calculating local network information 2 From a
global network.
There are multiple options when you have complete
network information. Type of tie Sent,
Received, or both? Once you decide on a type of
tie, you need to get the information of interest
in a form similar to that in the example above.
19
Calculating local network information 2 From a
global network.
An example network All senior males from a small
(n350) public HS.
20
Calculating local network information 2 From a
global network.
Suppose you want to identify egos friends,
calculate what proportion of egos female friends
are older than ego, and how many male friends
they have (this example came up in a model of
fertility behavior).

• You need to
• Construct a dataset with
• (a) ego's id. This allows you to link each
  person in the network.
• (b) age of each person,
• (c) the friendship nominations variables.
• Then you need to
• a) Identify ego's friends
• b) Identify their age
• c) compare it to ego's age
• d) count it if it is greater than ego's.
• There is a SAS program described in the exercise
  that shows you how to do this kind of work, using
  the graduate student network data.

21
Calculating local network information 2 From a
global network.
1) Go over how to translate network data from one
program to another UCINET PAJEK 2) Go over the
use of ego-net macros in SAS