Model Network Evolution with SAOM
Prepare repeated complete networks, test change capacity and convergence, and interpret selection and influence parameters within an explicit micro-step model.
Method sources
By the end of this tutorial
- 1Define stochastic actor-oriented models from an explicit node, tie, boundary, direction, weight, and observation-window specification.
- 2Apply and audit this procedure: Check Jaccard stability and opportunities for change, specify structural, selection and behavior effects before estimation, fit the SAOM, inspect convergence t-ratios and goodness of fit, and compare justified alternative specifications.
- 3Interpret the result with a sensitivity check and the following evidence boundary: SAOM parameters are conditional model effects, not direct causal estimates; sparse change, omitted context, period heterogeneity, and misspecification can make selection and influence difficult to separate.
SNA
Network specification
Analysis scenario
A school measures friendship and study engagement at four terms and asks whether students select similar peers, become similar after friendship, or both.
Nodes
The same eligible student roster reconciled across four survey waves, with entry, exit, and structurally missing periods documented.
Ties
Directed friendship nominations at each wave plus a repeatedly measured individual study-engagement behavior.
Network type
Longitudinal one-mode directed binary networks with four waves, actor covariates, a changing behavior, no self-ties, and explicit missingness.
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: Check Jaccard stability and opportunities for change, specify structural, selection and behavior effects before estimation, fit the SAOM, inspect convergence t-ratios and goodness of fit, and compare justified alternative specifications. 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: SAOM parameters are conditional model effects, not direct causal estimates; sparse change, omitted context, period heterogeneity, and misspecification can make selection and influence difficult to separate.
Checkpoint
The final note contains the question, specification, result, sensitivity evidence, uncertainty, privacy controls, and a proportionate next step.
Interpret with care
stochastic actor-oriented models describes a property of the specified relation and network boundary. It does not transfer automatically to another relation, time period, class, platform, or population.
SAOM parameters are conditional model effects, not direct causal estimates; sparse change, omitted context, period heterogeneity, and misspecification can make selection and influence difficult to separate. Compare the result with raw counts, missingness, plausible alternative specifications, and contextual evidence before acting.