Skip to content

Research at St Andrews

Multiple regressions: the meaning of multiple regression and the non-problem of collinearity

Research output: Contribution to journalArticlepeer-review


Simple regression (regression analysis with a single explanatory variable), and multiple regression (regression models with multiple explanatory variables), typically correspond to very different biological questions. The former use regression lines to describe univariate associations. The latter describe the partial, or direct, effects of multiple variables, conditioned on one another. We suspect that the superficial similarity of simple and multiple regression leads to confusion in their interpretation. A clear understanding of these methods is essential, as they underlie a large range of procedures in common use in biology. Beyond simple and multiple regression in their most basic forms, understanding the key principles of these procedures is critical to understanding, and properly applying, many methods, such as mixed models, generalised models, and causal inference using graphs (including path analysis and its extensions). A simple, but careful, look at the distinction between these two analyses is valuable in its own right, and can also be used to clarify widely-held misconceptions about collinearity (correlations among explanatory variables). There is no general sense in which collinearity is a problem. We suspect that the perception of collinearity as a hindrance to analysis stems from misconceptions about interpretation of multiple regression models, and so we pursue discussions about these misconceptions in this light. In particular, collinearity causes multiple regression coefficients to be less precisely estimated than corresponding simple regression coefficients. This should not be interpreted as a problem, as it is perfectly natural that direct effects should be harder to characterise than univariate associations. Purported solutions to the perceived problems of collinearity are detrimental to most biological analyses.


Original languageEnglish
Article number3
Number of pages24
JournalPhilosophy, Theory and Practice in Biology
Publication statusPublished - 2018

    Research areas

  • Regression, Multiple regression, Collinearity, Ordinary least squares, Linear model, Causal effect, Correlation

Discover related content
Find related publications, people, projects and more using interactive charts.

View graph of relations

Related by author

  1. Revisiting advice on the analysis of count data

    Morrissey, M. B. & Ruxton, G. D., 26 Jul 2020, In: Methods in Ecology and Evolution. Early View, 8 p.

    Research output: Contribution to journalArticlepeer-review

  2. Evaluation of disruptive camouflage of avian cup-nests

    Mulder, T., Campbell, C. & Ruxton, G. D., Jan 2021, In: Ibis. 163, 1, p. 150-158

    Research output: Contribution to journalArticlepeer-review

  3. Turn alternation and the influence of environmental factors on search routes through branched structures by ladybirds (Coccinella septempunctata and Adalia bipunctata)

    Humphreys, R. K., Neuhäuser, M. & Ruxton, G. D., 5 Dec 2020, In: Behavioural Processes. In-Press, 104292.

    Research output: Contribution to journalArticlepeer-review

  4. Quantifying the causal pathways contributing to natural selection

    Henshaw, J. M., Morrissey, M. B. & Jones, A. G., 12 Oct 2020, In: Evolution. Early View, 15 p.

    Research output: Contribution to journalArticlepeer-review

  5. Effective use of the McNemar test

    Pembury Smith, M. & Ruxton, G. D., 10 Oct 2020, In: Behavioral Ecology and Sociobiology. 74, 9 p., 133.

    Research output: Contribution to journalArticlepeer-review

ID: 253120157