Compare Networks Across Groups
Harmonize boundaries and tie opportunities, show distributions across networks, and avoid treating dependent dyads as independent observations.
Method sources
By the end of this tutorial
- 1Define multi-network group comparison from an explicit node, tie, boundary, direction, weight, and observation-window specification.
- 2Apply and audit this procedure: Create a harmonization table, use size-aware or normalized summaries, plot the full school distribution, apply permutation or hierarchical network methods that retain dependence, and run leave-one-school-out sensitivity.
- 3Interpret the result with a sensitivity check and the following evidence boundary: Raw density, path length, and centralization change with size, opportunity, response, and composition; a difference between schools is not automatically a program effect.
SNA
Network specification
Analysis scenario
A faculty-development program wants to compare advice networks in 24 schools that vary in roster size, response coverage, and formal team structure.
Nodes
The eligible staff roster separately defined for each school under the same census date and role rules.
Ties
A directed advice nomination using identical wording and observation windows in every school.
Network type
Twenty-four directed binary whole networks with school-level covariates, unequal sizes, retained isolates, and documented coverage.
Step-by-step tutorial
Freeze the relational question
Write the decision the analysis must inform, then lock the eligible node roster, tie-generating event, direction, weight, self-tie rule, observation window, and missing-data code. Preserve a read-only source copy and record why this specification represents the stated question.
Checkpoint
A second analyst can reconstruct the same node set and edge table from the written rules without guessing what an absent record means.
Compute the focal structure
Work on a versioned analysis copy and carry out the focal method exactly as specified: Create a harmonization table, use size-aware or normalized summaries, plot the full school distribution, apply permutation or hierarchical network methods that retain dependence, and run leave-one-school-out sensitivity. Save software and package versions, every threshold, normalization, seed, and intermediate count needed to reproduce the result.
Checkpoint
The output is tied to one named data version and includes the denominator, parameter settings, and a reproducible calculation record.
Run a structural sensitivity check
Repeat the analysis under at least one defensible alternative boundary, missingness rule, tie threshold, weight transformation, or model setting. Compare membership and substantive conclusions, not only a single coefficient, and investigate every change large enough to alter a decision.
Checkpoint
The audit states which patterns persist, which actors or groups change classification, and which conclusion depends on an analyst choice.
Report for responsible action
Pair the numerical result with a table or structure-preserving visual, document excluded and missing actors, and explain uncertainty in plain language. Convert the finding into a reversible support question, not an automatic ranking, while stating this boundary: Raw density, path length, and centralization change with size, opportunity, response, and composition; a difference between schools is not automatically a program effect.
Checkpoint
The final note contains the question, specification, result, sensitivity evidence, uncertainty, privacy controls, and a proportionate next step.
Interpret with care
multi-network group comparison describes a property of the specified relation and network boundary. It does not transfer automatically to another relation, time period, class, platform, or population.
Raw density, path length, and centralization change with size, opportunity, response, and composition; a difference between schools is not automatically a program effect. Compare the result with raw counts, missingness, plausible alternative specifications, and contextual evidence before acting.