Regression modelSocial PsychologyDyadic / interpersonal data analysisModel

Social Relations Model

Also known as: SRM, Kenny Social Relations Model, Round-Robin Variance Partition

OriginatorDavid A. Kenny and colleaguesYear2006Sources1Related methods8

The Social Relations Model (SRM), developed by David Kenny and colleagues, is a variance-decomposition framework for analyzing interpersonal perception and behavior in groups. When every member of a group rates (or behaves toward) every other member in a round-robin design, each rating reflects three distinct sources: the perceiver's general tendency to see others a certain way (actor effect), the target's general tendency to be seen that way by others (partner effect), and the unique adjustment a particular perceiver makes for a particular target (relationship effect), plus error. The SRM partitions the total variance into these components and estimates two kinds of reciprocity -- generalized (do people who like others tend to be liked?) and dyadic (do specific pairs uniquely reciprocate?). By separating the perceiver, the target, and their unique relationship, the SRM answers fundamental questions about whether interpersonal judgments lie in the eye of the beholder, the qualities of the person judged, or the chemistry of the dyad.

Key highlights

  • Separates perceiver, target, and relationship sources of interpersonal data.
  • Estimates both generalized and dyadic reciprocity.
  • Answers foundational questions about the locus of interpersonal judgments.
  • Applicable to perception, behavior, and many interpersonal constructs.

Intuition

This section is available to Pro members. Upgrade to Pro

How it works

This section is available to Pro members. Upgrade to Pro

When to use it

Use the Social Relations Model when you have round-robin or block dyadic data and want to know how much of interpersonal perception or behavior is due to the perceiver, the target, or the unique relationship, and whether perceptions are reciprocated. It is ideal for studying interpersonal perception, attraction, trust, and behavior in groups, families, and teams. It is less appropriate when data are not structured so that members both rate and are rated by multiple others (the design requirement), when groups are too small to estimate components reliably, or when only a single directed relationship per person is observed (where the APIM is more suitable). Adequate group sizes and, often, multiple groups are needed for stable estimates.

Strengths & limitations

Strengths
  • Separates perceiver, target, and relationship sources of interpersonal data.
  • Estimates both generalized and dyadic reciprocity.
  • Answers foundational questions about the locus of interpersonal judgments.
  • Applicable to perception, behavior, and many interpersonal constructs.
Limitations
  • Requires demanding round-robin or block designs with each member rating many others.
  • Needs adequately sized and often multiple groups for stable variance estimates.
  • Estimation and interpretation are more complex than standard models.
  • Missing data and unequal group sizes complicate analysis.

Common pitfalls

This section is available to Pro members. Upgrade to Pro

Applications

This section is available to Pro members. Upgrade to Pro

Frequently asked

What three components does the SRM separate?

The SRM partitions each interpersonal observation into an actor effect (the perceiver's general tendency to rate or behave toward others a certain way), a partner effect (the target's general tendency to be rated or treated that way by others), and a relationship effect (the unique adjustment a specific perceiver makes for a specific target), plus error. This answers whether a judgment lies in the beholder, the target, or the dyad.

What is the difference between generalized and dyadic reciprocity?

Generalized reciprocity is the correlation between a person's actor and partner effects -- for example, whether people who generally like others are generally liked in return. Dyadic reciprocity is the correlation between the two relationship effects within a specific pair -- whether unique liking is mutual beyond general tendencies. The SRM estimates both, which ordinary analyses cannot distinguish.

Why does the SRM need a round-robin design?

To separate actor, partner, and relationship variance, each person must serve as both perceiver and target multiple times, which requires that everyone in a group rate everyone else. This crossed, balanced structure is exactly what the round-robin design provides; without it, the perceiver, target, and relationship contributions are confounded and cannot be decomposed.

Sources

  1. 1.
    Kenny, D. A., Kashy, D. A., & Cook, W. L. (2006). Dyadic Data Analysis. Guilford Press.
    ISBN 9781572309869

You have read it. What now?

Cite this page

ScholarGate. (2026, June 23). Social Relations Model. ScholarGate. https://scholargate.app/social-psychology/social-relations-model