Skip to main content

Advertisement

Log in

Sameness and Difference in Psychological Research on Consensually Non-Monogamous Relationships: The Need for Invariance and Equivalence Testing

  • Special Section: Consensual Non-monogamy
  • Published:
Archives of Sexual Behavior Aims and scope Submit manuscript

Abstract

Comparative research involving consensually non-monogamous (CNM) relationships and outcomes related to well-being continues to grow as an area of interest within sexual science. However, claims of sameness and/or difference between groups rely on two critical, yet widely under-appreciated assumptions: that the concepts being compared between groups are the same (i.e., measurement invariance), and that logically and statistically coherent procedures are used for evaluating sameness (i.e., equivalence testing). We evaluated the state of measurement invariance and equivalence across three studies, involving different types of CNM comparisons (i.e., relationship types, partner types) and designs (analysis of primary individual data, primary dyadic data, and secondary data). Our invariance tests of CNM compared to monogamous individuals (Study 1) and “primary” compared to “secondary” partners in dyadic appraisal of CNM individuals (Study 2) revealed that many measures of well-being failed to replicate their measurement models and were not generalizable across relationship types or partner types. Our reanalyses of existing comparative CNM effects using individual and meta-analyzed equivalence tests (Study 3), meanwhile, indicated that this literature requires more consistent reporting practices and larger samples, as most studies produced uninformative tests of equivalence. Our results illustrate the importance of auxiliary hypothesis evaluation and statistical procedure selection for generating informative comparative tests. Our findings also highlight potential divergences in social construction of well-being. We offer suggestions for researchers, reviewers, and editors in terms of needed methodological reforms for future comparative CNM research.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Notes

  1. We use the descriptor “ostensible” because it is often the methodological tradition that researchers assume that individuals reporting to be in single-partnered relationships actually remain faithful to their partners. However, ample evidence suggests that infidelity in these single-partnerships is not only possible, but frequent (e.g., Mark, Janssen, & Milhausen, 2011). We therefore think it is important to highlight that the actual state of monogamy in this comparative literature is tacitly assumed, and not scientifically observed.

  2. Credibility (or prediction) intervals are the Bayesian analog to the Frequentist/NHST confidence intervals (see Dienes, 2008). Credibility intervals provide a range of values within which the true population parameter is likely (e.g., 95%) to fall (see Borenstein, Higgins, Hedges, & Rothstein, 2017), whereas confidence intervals provide a range of values that, across many random resamples from the same population, are expected to capture the true population parameter a certain percentage of the time (e.g., 95%) (see https://rpsychologist.com/d3/CI/ for an accessible visualization). Somewhat ironically, most researchers misinterpret confidence intervals as providing the kind of (intuitive) inference that a credibility interval provides.

References

Download references

Acknowledgments

This research was supported by a SSHRC Insight Development Grant awarded to Dr. Sakaluk and a SSHRC Joseph-Armand Bombardier Canada Graduate Scholarship (S1 and S2 funding) awarded to Dr. Wood.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to John K. Sakaluk.

Ethics declarations

Conflict of interest

The authors declare that they have no conflicts of interest.

Ethical Approval

All procedures performed in studies involving human participants (Studies 1 and 2) were approved by the Research Ethics Board of the University of Guelph.

Informed Consent

We obtained informed consent from all individual participants included in Studies 1 and 2.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Sakaluk, J.K., Quinn-Nilas, C., Fisher, A.N. et al. Sameness and Difference in Psychological Research on Consensually Non-Monogamous Relationships: The Need for Invariance and Equivalence Testing. Arch Sex Behav 50, 1341–1365 (2021). https://doi.org/10.1007/s10508-020-01794-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10508-020-01794-9

Keywords

Navigation