Using fractional polynomials to model non‐linear trends in longitudinal data
The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
Non‐linear growth curves are discussed within the context of the linear mixed model. Non‐linearity is modelled with time transformations known as fractional polynomials (FPs) having power terms that can be negative values and fractions with conventional polynomials (CPs) as a special case. Issues of interpretation are discussed with a focus on the instantaneous rate of change in models with and without static correlates. Methods for model selection are presented with emphasis on penalized and non‐penalized indices of global fit based on the maximized likelihood and fitted models. Two empirical examples are presented with psychological data in which FPs were fitted along with CPs of equal and next highest order. The results show that the FPs had equal or better fit than the higher‐order CPs and had prediction curves with as favourable or more favourable characteristics, such as less extreme behaviour at the edges of the observed time intervals. The results illustrate some of the potential advantages of FPs relative to CPs, which include parsimony, flexibility of curve shape, and the ability to approximate asymptotes. Though FPs are not necessarily suggested as replacements for CPs or other transformations (e.g. piecewise models), they might be useful when the goal is to model non‐linear growth trends with smooth curves.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Multimodel Inference: Understanding AIC and BIC in Model Selection
Burnham, K. P., & Anderson, D. R. (2004) · Sociological Methods & Research · doi:10.1177/0049124104268644 · Cited by 11,648 · cited 1×
“In fact, it has been argued that single-model selection can be biased and multi-model inference based on fit indices for all models under consideration is a more desirable approach (Burnham & Anderson, 2004).”
BackgroundMaximum Likelihood Approaches to Variance Component Estimation and to Related Problems
Harville, D. A. (1977) · Journal of the American Statistical Association · doi:10.1080/01621459.1977.10480998 · Cited by 2,667
The use of fractional polynomials to model continuous risk variables in epidemiology
Royston, P., Ambler, G., & Sauerbrei, W. (1999) · International Journal of Epidemiology · doi:10.1093/ije/28.5.964 · Cited by 1,066
The Analysis of Social Science Data with Missing Values
LITTLE, R. J. A., & RUBIN, D. B. (1989) · Sociological Methods & Research · doi:10.1177/0049124189018002004 · Cited by 1,016 · cited 1×
“Handling of such imbalance is a strength of LMM under the assumption that the data are at least missing at random (Little & Rubin, 1989).”
Selecting the Best Linear Mixed Model Under REML
Gurka, M. J. (2006) · The American Statistician · doi:10.1198/000313006x90396 · Cited by 200 · cited 1×
“Because the selection of an FP model focuses on fixed effects, we stress the use of maximum likelihood, though there is evidence that REML may be used with the above measures (Gurka, 2006).”
Method
Research works printed but not linked: 38
- Bates D., 2005, Fitting linear mixed models in R, R News, 5, 27
- Belsley D. A., 2004, Regression diagnostics: Identifying influential data and sources of collinearity
- 10.1002/0471746096 · DOI · Paper page
- 10.1080/00401706.1962.10490038 · DOI · Paper page
- 10.1093/oxfordjournals.schbul.a033485 · DOI · Paper page
- 10.1037/0022-006X.65.3.464 · doi:10.1037/0022-006x.65.3.464 · Paper page
- Cleveland W. S., 1992, Statistical models in S
- 10.1207/s15327906mbr3103_6 · DOI · Paper page
- 10.1037/1082-989X.7.1.41 · doi:10.1037/1082-989x.7.1.41 · Paper page
- 10.2307/2531727 · DOI · Paper page
- 10.1093/oso/9780198524847.001.0001 · DOI · Paper page
- 10.1080/01621459.1995.10476599 · doi:10.1080/01621459.1995.10476599
- 10.1002/sim.1991 · DOI · Paper page
- Emerson J. D., 1983, Understanding robust and exploratory data analysis, 97
- 10.1198/jasa.2009.0116 · DOI · Paper page
- 10.1214/ss/1177011136 · DOI · Paper page
- 10.1007/BF01840837 · DOI
- Hastie T., 1990, Generalized additive models
- 10.1198/016214504000000269 · DOI · Paper page
- 10.2307/2529876 · DOI · Paper page
- 10.1037/10099-010 · DOI
- 10.1007/BF02294746 · DOI · Paper page
- Mosteller F., 1977, Data analysis and regression: A second course
- Nelson C. A., 2001, Handbook of developmental cognitive neuroscience, 125
- 10.1016/j.csda.2007.06.006 · DOI
- 10.2307/2986270 · DOI · Paper page
- 10.1111/1467-9884.00093 · doi:10.1111/1467-9884.00093
- 10.1055/s-0038-1634008 · DOI · Paper page
- 10.1016/j.csda.2006.05.006 · DOI
- Royston P., 2008, Multivariate model‐building, 10.1002/9780470770771 · DOI · Paper page
- Runge C., 1901, über empirische Funktionen und die Interpolation zwischen äquidistanten Ordinaten [On empirical functions and the interpolation between equidistant ordinates], Zeitschrift für Mathematik und Physik, 46, 224
- 10.1198/108571102780 · DOI
- Verbeke G., 2000, Linear mixed models for longitudinal data
- Vonesh E. F., 1997, Linear and non‐linear models for the analysis of repeated measurements
- 10.2307/2682803 · DOI
- 10.1111/j.1467-7687.2005.00452.x · DOI · Paper page
- West B. T., 2007, Linear mixed models
- 10.1002/sim.1572 · DOI · Paper page
Cited by
Obradović, J., Long, J. D., Cutuli, J. J., Chan, C.-K., Hinz, E., Heistad, D., & Masten, A. S. (2009) · Development and Psychopathology · doi:10.1017/s0954579409000273 · Cited by 259
Self-citationCutuli, J. J., Desjardins, C. D., Herbers, J. E., Long, J. D., Heistad, D., Chan, C.-K., Hinz, E., & Masten, A. S. (2013) · Child Development · doi:10.1111/cdev.12013 · Cited by 235
“With this in mind, we examined the plausibility of linear versus nonlinear growth curves, with the latter being either a quadratic polynomial, or a more parsimonious model using the log transformation of time (Long & Ryoo, 2010).”
MethodSelf-citationAnalysis of cluster randomised stepped wedge trials with repeated cross-sectional samples
Hemming, K., Taljaard, M., & Forbes, A. (2017) · Trials · doi:10.1186/s13063-017-1833-7 · Cited by 166
“With a large number of steps, or where time is recorded continuously, it should also be possible to model the secular trend using quadratic or cubic terms, or even fractional polynomials [32] or restricted cubic splines.”
BackgroundThe Shape of the Dose-Response Relationship between Sugars and Caries in Adults
Bernabé, E., Vehkalahti, M. M., Sheiham, A., Lundqvist, A., & Suominen, A. L. (2016) · Journal of Dental Research · doi:10.1177/0022034515616572 · Cited by 145
Metadata
- Authors
- Long, J., & Ryoo, J.
- Venue
- British Journal of Mathematical and Statistical Psychology
- Publisher
- Wiley
- Published
- 2010-02
- Volume
- 63
- Issue
- 1
- Pages
- 177-203
- ISSN
- 0007-1102 (ISSN-L)
- 2044-8317
- OpenAlex
- W2038084400
- Cited by
- 82
- References
- 5
- FWCI
- 4.92
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Using fractional polynomials to model non‐linear trends in longitudinal data. https://app.cochat.ai/papers/10.1348/000711009x431509
- The paper
- Long, J., & Ryoo, J. (2010). Using fractional polynomials to model non‐linear trends in longitudinal data. British Journal of Mathematical and Statistical Psychology. https://doi.org/10.1348/000711009x431509
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.