Maximum Likelihood Estimation of Non-Normal Random Effects and Random Errors in Nonlinear Random Effects Models

Abstract

Nonlinear random effects models (NREMs) are particularly useful for modeling longitudinal data that follow intrinsically nonlinear trends. However, NREMs assume both random effects and random errors to be normally distributed, which is likely violated when the outcome variable does not appear normal. No existing software under the frequentist framework provides researchers the flexibility to specify non-normal random effects to date. To address this significant gap in the application and research of NREMs, we developed an R routine NEfit.R that allows the specification of non-normal random effects and random errors using Gauss-Hermite Quadrature approximation and Newton-Raphson iteration. This study includes a motivating real-data application and a comprehensive Monte Carlo simulation study that supports the robustness of the performance of NEfit.R.

Keywords

longitudinal data intrinsically nonlinear random effects models non-normal random effects non-normal random errors

Get full access to this article

View all access options for this article.

References

Akaike

(1974). A new look at the statistical model identification. IEEE Transactions on Automatic Control, 19(6), 716–723. https://doi.org/10.1109/TAC.1974.1100705

Bates

Mächler

Bolker

Walker

(2015). Fitting linear mixed-effects models using lme4. Journal of Statistical Software, 67(1), 1–48. https://doi.org/10.18637/jss.v067.i01

Bates

D. M.

Watts

D. J.

(1988). Nonlinear regression analysis and its applications. Wiley. https://doi.org/10.1002/9780470316757

Blanca

M. J.

Arnau

López-Montiel

Bono

Bendayan

(2013). Skewness and kurtosis in real data samples. Methodology, 9(2), 78–84. https://doi.org/10.1027/1614-2241/a000057

Blozis

S. A.

(2004). Structured latent curve models for the study of change in multivariate repeated measures. Psychological Methods, 9(3), 334–353. https://doi.org/10.1037/1082-989X.9.3.334

Broström

Holmberg

(2011). Generalized linear models with clustered data: Fixed and random effects models. Computational Statistics & Data Analysis, 55(12), 3123–3134. https://doi.org/10.1016/j.csda.2011.06.011

Broström

Jin

Holmberg

(2024). glmmML: Generalized linear models with clustering. (R package version 1.1.7) [Computer software]. https://CRAN.R-project.org/package=glmmML

Bürkner

P. C.

(2017). brms: An R package for Bayesian multilevel models using Stan. Journal of Statistical Software, 80(1), 1–28. https://doi.org/10.18637/jss.v080.i01

Clarke

Crawford

Steele

Vignoles

A. F.

(2010). The choice between fixed and random effects models: Some considerations for educational research (IZA discussion paper no. 5287). Institute for the Study of Labor. https://doi.org/10.2139/ssrn.1700456

10.

Comets

Lavenu

Lavielle

(2017). Parameter estimation in nonlinear mixed effect models using saemix, an R implementation of the SAEM algorithm. Journal of Statistical Software, 80(3), 1–41. https://doi.org/10.18637/jss.v080.i03

11.

Davidian

Gallant

(1993). The nonlinear mixed effects model with a smooth random effects density. Biometrika, 80(3), 475–488. https://doi.org/10.2307/2337169

12.

Davidian

Giltinan

D. M.

(2003). Nonlinear models for repeated measurement data: An overview and update. Journal of Agricultural, Biological, and Environmental Statistics, 8(4), 387–419. https://doi.org/10.1198/1085711032697

13.

Dempster

A. P.

Laird

N. M.

Rubin

D. B.

(1977). Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society. Series B, Methodological, 39(1), 1–38. https://doi.org/10.1111/j.2517-6161.1977.tb01600.x

14.

Drikvandi

(2020). Nonlinear mixed-effects models with misspecified random-effects distribution. Pharmaceutical Statistics: The Journal of the Pharmaceutical Industry, 19(3), 187–201. https://doi.org/10.1002/pst.1981

15.

Dumas

D. G.

McNeish

D. M.

(2017). Dynamic measurement modeling: Using nonlinear growth models to estimate student learning capacity. Educational Researcher, 46(6), 284–292. https://doi.org/10.3102/0013189X17725747

16.

du Toit

S. H. C.

Cudeck

(2009). Estimation of the nonlinear random coefficient model when some random effects are separable. Psychometrika, 74(1), 65–82. https://doi.org/10.1007/s11336-008-9107-7

17.

Elvira

Closas

Martino

(2019). Gauss-Hermite quadrature for non-Gaussian inference via an importance sampling interpretation [Conference presentation]. 2019 27th European Signal Processing Conference (EUSIPCO), A Coruña, Spain. https://doi.org/10.23919/EUSIPCO.2019.8902662

18.

Grimm

K. J.

Ram

Hamagami

(2011). Nonlinear growth curves in developmental research. Child Development, 82(5), 1357–1371. https://doi.org/10.1111/j.1467-8624.2011.01630.x

19.

Gurka

M. J.

Kelley

G. A.

Edwards

L. J.

(2012). Fixed and random effects models. Computational Statistics, 4(2), 181–190. https://doi.org/10.1002/wics.201

20.

Harring

J. R.

Liu

(2016). A comparison of estimation methods for nonlinear mixed effects models under model misspecification and data sparseness: A simulation study. Journal of Modern Applied Statistical Methods, 15(1), 539–569. https://doi.org/10.22237/jmasm/1462076760

21.

Hartford

Davidian

(2000). Consequences of misspecifying assumptions in nonlinear mixed effects models. Computational Statistics & Data Analysis, 34(2), 139–164. https://doi.org/10.1016/S0167-9473(99)00076-6

22.

Harwell

(2019). A strategy for using bias and RMSE as outcomes in Monte Carlo studies in statistics. Journal of Modern Applied Statistical Methods, 17(2), Article 991. https://doi.org/10.22237/jmasm/1551907966

23.

Heagerty

P. J.

Kurland

B. F.

(2001). Misspecified maximum likelihood estimates and generalised linear mixed models. Biometrika, 88(4), 973–985. https://doi.org/10.1093/biomet/88.4.973

24.

Hui

F. K. C.

Müller

Welsh

A. H.

(2021). Random effects misspecification can have severe consequences for random effects inference in linear mixed models. International Statistical Review, 89(1), 186–206. https://doi.org/10.1111/insr.12378

25.

Kohli

Harring

J. R.

Hancock

G. R.

(2013). Piecewise linear–linear latent growth mixture models with unknown knots. Educational and Psychological Measurement, 73(6), 935–955. https://doi.org/10.1177/0013164413496812

26.

Kohli

Harring

J. R.

Zopluoglu

(2016). A finite mixture of nonlinear random coefficient models for continuous repeated measures data. Psychometrika, 81(3), 851–880. https://doi.org/10.1007/s11336-015-9462-0

27.

Kohli

Hughes

Wang

Zopluoglu

Davison

M. L.

(2015). Fitting a linear–linear piecewise growth mixture model with unknown knots: A comparison of two common approaches to inference. Psychological Methods, 20(2), 259–275. https://doi.org/10.1037/met0000034

28.

Kohli

Sullivan

A. L.

(2019). Linear-linear piecewise growth mixture models with unknown random knots: A primer for School Psychology. Journal of School Psychology, 73, 89–100. https://doi.org/10.1016/j.jsp.2019.03.004

29.

Laird

N. M.

Ware

J. H.

(1982). Random-effects models for longitudinal data. Biometrics, 38(4), 963–974. https://doi.org/10.2307/2529876

30.

Lakens

(2013). Calculating and reporting effect sizes to facilitate cumulative science: A practical primer for t-tests and ANOVAs. Frontiers in Psychology, 4, Article 863. https://doi.org/10.3389/fpsyg.2013.00863

31.

Lin

T. I.

Lee

J. C.

(2008). Estimation and prediction in linear mixed models with skew-normal random effects for longitudinal data. Statistics in Medicine, 27(9), 1490–1507. https://doi.org/10.1002/sim.3026

32.

Lindstrom

M. J.

Bates

D. M.

(1988). Newton-Raphson and EM algorithms for linear mixed effects models for repeated-measures data. Journal of the American Statistical Association, 83(404), 1014–1022. https://doi.org/10.1080/01621459.1988.10478693

33.

Lindstrom

M. J.

Bates

D. M.

(1990). Nonlinear mixed effects models for repeated measures data. Biometrics, 46(3), 673–687. https://doi.org/10.2307/2532087

34.

Lock

E. F.

Kohli

Bose

(2018). Detecting multiple random changepoints in Bayesian piecewise growth mixture models. Psychometrika, 83(3), 733–750. https://doi.org/10.1007/s11336-017-9594-5

35.

Mathai

A. M.

Moschopoulos

P. G.

(1991). On a multivariate gamma. Journal of Multivariate Analysis, 39(1), 135–153. https://doi.org/10.1016/0047-259X(91)90010-Y

36.

McCulloch

C. E.

Neuhaus

J. M.

(2011). Misspecifying the shape of a random effects distribution: Why getting it wrong may not matter. Statistical Science, 26(3), 388–402. https://doi.org/10.1214/11-STS361

37.

Meza

Osorio

De la Cruz

(2012). Estimation in nonlinear mixed-effects models using heavy-tailed distributions. Statistics and Computing, 22(1), 121–139. https://doi.org/10.1007/s11222-010-9212-1

38.

Nelson

K. P.

Lipsitz

S. R.

Fitzmaurice

G. M.

Ibrahim

Parzen

Strawderman

(2006). Use of the probability integral transformation to fit nonlinear mixed-effects models with nonnormal random effects. Journal of Computational and Graphical Statistics, 15(1), 39–57. https://doi.org/10.1198/106186006X96854

39.

Peralta

Kohli

Lock

E. F.

Davison

M. L.

(2022). Bayesian modeling of associations in bivariate piecewise linear mixed-effects models. Psychological Methods, 27(1), 44–64. https://doi.org/10.1037/met0000358

40.

Pinheiro

J. C.

Bates

D. M.

(1995). Approximations to the log-likelihood function in the nonlinear mixed-effects model. Journal of Computational and Graphical Statistics, 4(1), 12–35. https://doi.org/10.1080/10618600.1995.10474663

41.

Pinheiro

J. C.

Bates

, & R Core Team (2024). nlme: Linear and nonlinear mixed effects models. (R package version 3.1-167) [Computer software]. https://CRAN.R-project.org/package=nlme

42.

Pinheiro

J. C.

Liu

Y. N.

(2001). Efficient algorithms for robust estimation in linear mixed-effects models using the multivariate t distribution. Journal of Computational and Graphical Statistics, 10(2), 249–276. https://doi.org/10.1198/10618600152628059

43.

R Core Team. (2023). R: A language and environment for statistical computing (Version 3.1-164). R Foundation for Statistical Computing. https://www.r-project.org/.

44.

R Core Team. (2024). R: A language and environment for statistical computing. R Foundation for Statistical Computing. https://www.R-project.org/

45.

Raudenbush

S. W.

Bryk

A. S.

(2002). Hierarchical linear models: Applications and data analysis methods (2nd ed.). Sage Publications.

46.

Rohloff

C. T.

Kohli

Chung

(2023). The impact of functional form complexity on model overfitting for nonlinear mixed-effects models. Multivariate Behavioral Research, 58(4), 723–742. https://doi.org/10.1080/00273171.2022.2119360

47.

Rohloff

C. T.

Kohli

Lock

E. F.

(2024). Identifiability and estimability of Bayesian linear and nonlinear crossed random effects models. British Journal of Mathematical & Statistical Psychology, 77(2), 375–394. https://doi.org/10.1111/bmsp.12334

48.

SAS Institute Inc. (2014). The NLMIXED procedure. In SAS/STAT® 13.2 user’s guide (pp. 5682–5781). https://support.sas.com/documentation/onlinedoc/stat/132/nlmixed.pdf

49.

Schumacher

F. L.

Dey

D. K.

Lachos

V. H.

(2021). Approximate inferences for nonlinear mixed effects models with scale mixtures of skew-normal distributions. Journal of Statistical Theory and Practice, 15(3), Article 60. https://doi.org/10.1007/s42519-021-00172-5

50.

Schwarz

(1978). Estimating the dimension of a model. The Annals of Statistics, 6(2), 461–464. https://doi.org/10.1214/aos/1176344136

51.

Spearman

C. C.

(1904). The proof and measurement of association between two things. American Journal of Psychology, 15, 72–101. https://doi.org/10.2307/1422689https://www.jstor.org/stable/1422689

52.

Stegmann

Jacobucci

Harring

J. R.

Grimm

K. J.

(2018). Nonlinear mixed-effects modeling programs in R. Structural Equation Modeling, 25(1), 160–165. https://doi.org/10.1080/10705511.2017.1396187

53.

Zhang

Kohli

Lock

E. F.

(2024). Bayesian (non)linear random effects mediation models: Evaluating the impact of omitting confounders. Psychological Methods. Advance online publication. https://doi.org/10.1037/met0000721

54.

Zopluoglu

Harring

J. R.

Kohli

(2014). FitPMM: An R routine to fit finite mixture of piecewise mixed–effect models with unknown random knots. Applied Psychological Measurement, 38(7), 583–584.

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.05 MB