Problems 1.1-1.3
Introduction

Questions are given in black, responses are given in blue (and are preceded by a bullet point).

  1. For each of the research problems described below, which are the nodes in the network study? And what is the network relation being considered? For each of the research problems described below, which are the nodes in the network study? And what is the network relation being considered?

    a. In a coeducational summer camp for teens, researchers want to know the extent to which attitudes about religion play a role in the formation of friendships within the first week of coming to camp.

    • The nodes are individual teens, and network relation is friendship.

    • The level of analysis is the dyad

    • The dependent variable (DV) is presence/absent of a friendship tie and independent variables (IV) are based on attitudes about religion


b. An anthropologist is interested in studying the relationship between Canadian Inuit hunters’ structural position in a hunting advice network, as measured by indegree centrality, and their hunting success.

  • The nodes are individual hunters, and the network relation is ‘who seeks hunting advice from whom’.

  • The level of analysis is the node

  • The DV is hunting success and the IV is indegree centrality


c. A sports psychologist is interested in studying the relationship between basketball team cohesion off the court and the number of regular-season wins among a sample of 30 US universities.

.

  • The nodes are basketball team players, the network relation is unspecified except that it involves ‘cohesion’ – could be something trust or warmth.

  • The unit of analysis will be the team, of which there are 30.

  • The independent variable is team cohesion, and the dependent variable is team performance


d. A political scientist hypothesizes a relationship between the presence of international trade relations and the formation of bilateral defense agreements.

  • The nodes are (probably) countries. There are two network relations being studied. One is trade and the other is 'has a defense agreement'.

  • The unit of analysis is the dyad.

  • Trade is being used as the independent variable. Having a defense agreement is the dependent variable.

e. An agricultural extension researcher proposes that time of adoption of a new fertilizer among Iowa corn farmers is related to the structural centrality of farmers in a communication network.

    • The nodes are farmers, and the network relation is ‘who communicates with whom’.

    • The (most appropriate) unit of analysis is the dyad.

    • The independent variable is structural similarity, and the dependent variable similarity in adoption time.

f. An organizational sociologist hypothesizes that the more regional sales teams have a centralized information-sharing network, the greater each team’s overall sales.

  • The nodes are salespeople, and the network relation is ‘who shares information with whom’.

  • The unit of analysis is the team.

  • The independent variable is team centralization, and the dependent variable is performance (as measured by sales).

g. An educational researcher is interested in how the political views of incoming freshmen at a large university affect the formation of friendship ties over the first semester.

  • The nodes are students, and the network relation is friendship.

  • The (most appropriate) unit of analysis is the dyad.

  • The independent variable is probably similarity of political views, although one might hypothesize that everyone avoids extremists, regardless of bent. The dependent variable is presence/absence of a friendship tie.

h. A psychologist is interested in the relationship between an astronaut’s knowledge of a mission team’s network structure and psychological well-being over the course of a 30-day simulated mission.

  • The nodes are astronauts. The network relation has not been specified.

  • The unit of analysis is the node.

  • The researcher will essentially use an astronaut’s social acumen to predict their mental health.

h. A management researcher hypothesizes that highly centralized networks are more efficient at a variety of task settings than evenly-distributed networks and designs an experiment to test this hypothesis.

  • The nodes are unspecified, but one imagines they are members of an organization. The network relation is also unspecified, but in this kind of research it is common to use ‘who communicates with whom about work tasks’ as the relation.

  • The unit of analysis is the group (probably a set of teams or departments. The question actually says it is the 'network' but it means the network within a group of some kind

  • The independent variable is the extent of centralization of the network, and the dependent variable is efficiency.

2. Consider each of the research problems identified in Problem 1.

a. There are normally three levels of analysis in the study of social networks: the dyadic level, node level and network level. For each of the research problems, what level of analysis is appropriate?

  • See responses to Question 1

b. For each of the problems, identify the explanatory variable and the outcome variable. Which is a network, and which a non-network variable?

  • See responses to Question 1

3. Based on the taxonomy of relations in Table 1.2, what categories would you place each of the following ties in? Explain your answer.

a. International trade among countries

  • Flows.

b. Financial transactions among banks

  • Relational events, specifically interactions.

c. Preschool children’s stated play preferences

  • Affective ties.

d. College student attendance at university functions

  • Participation.

e. Who one trusts in an organization

  • Affective.

f. Advice-seeking among scientific research team members

  • Nominally, interactions. However, when asked as ‘who do you regularly seek advice from’, it becomes a kind of relational role (‘advisor’).

g. Who one talks to about important matters

  • Although conversations are relational events, this is phrased as if it is an ongoing relationship, such as might be labeled by a relational role like ‘confidant’.

h. Money lending in a rural Indian community

  • See answer to ‘f’. If recorded as a series of time-stamped events, then they are relational events. But such data could be used to infer a relational state such as trust.

i. Conflict among ethnic groups in South Sudan

  • See answer to ‘f’. To the extent the conflict is repeated, it probably indicates an underlying role relation, such as ‘enemy’, or an affective relation such as ‘hates’.

j. As a member of a small project team, which colleagues one enjoys working with

  • Affective tie

k. Who one would want to work with on future projects in a high-tech firm

  • A mental relation. Clearly contains a perceptual element, but probably also reflects an affective component.

l. Sexual relationships among intravenous drug users

  • See answer to ‘f’. Having sex with someone is a relational event. Having a “sexual relationship” with someone suggests a relational role (‘lover’) that is ongoing.

m. Lab proximity of scientists in a research institute

  • Similarity, specifically with respect to location. Probably recorded as 2-mode data and then converted to 1-mode data

n. The observed interactions at a company picnic

  • Shenanigans. Interactions.

o. Members of parliament and their votes on policy issues

  • Similarities.