Institut de Santé Publique,
d'Épidémiologie et de Développement

Centre Inserm U897
Equipe Biostatistique

HETMIXSURV program V2.0

Cécile Proust-Lima

A Fortran90 program for the analysis of multivariate curvilinear possibly heterogeneous longitudinal outcomes and right-censored, left-truncated multi-cause time-to-event: a latent process and latent class approach


In its current version (V2.0), the program HETMIXSURV estimates a variety of statistical models including:

  1. univariate mixed model for curvilinear longitudinal outcome or ordinal outcome (see Proust-Lima, AJE 2011 for further details).

  2. multivariate mixed model for curvilinear and/or ordinal longitudinal outcomes (see Proust, Bcs 2006 and Proust-Lima, BMSP 2012 for further details).

  3. extension of 1. and 2. to the study of heterogeneous populations using latent classes of trajectory (see Proust, CMPB 2005, Proust-Lima, tech report 2015)

  4. extension of 1. and 2. to the joint analysis of a censored possibly truncated and multi-cause time-to-event in a joint latent class model (see Proust-Lima, CSDA 2009, Proust-Lima, SMMR 2012, Proust-Lima Arxiv 2015)

These models are estimated by a direct maximisation of the log-likelihood using a Marquardt algorithm. The use of the program including data importation, model specification and outputs is detailed in the readme.txt. The statistical methodology behind this program and the estimation procedure are detailed in the references given below.

Some of these models can also be estimated in R with the package lcmm (link cran:


Proust, C., & Jacqmin-Gadda, H. (2005). Estimation of linear mixed models with a mixture of distribution for the random effects. Computer Methods and Programs in Biomedicine, 78(2), 165-173. doi:10.1016/j.cmpb.2004.12.004

Proust, C., Jacqmin-Gadda, H., Taylor, J. M. G., Ganiayre, J., & Commenges, D. (2006). A nonlinear model with latent process for cognitive evolution using multivariate longitudinal data. Biometrics, 62(4), 1014-1024. doi:10.1111/j.1541-0420.2006.00573.x

Proust-Lima, C., Amieva, H., & Jacqmin-Gadda, H. (2013). Analysis of multivariate mixed longitudinal data: a flexible latent process approach. The British Journal of Mathematical and Statistical Psychology, 66(3), 470-487. doi:10.1111/bmsp.12000

Proust-Lima, C., Dartigues, J.-F., & Jacqmin-Gadda, H. (2011). Misuse of the linear mixed model when evaluating risk factors of cognitive decline. American Journal of Epidemiology, 174(9), 1077-1088. doi:10.1093/aje/kwr243

Proust-Lima, C., Dartigues, J.-F., & Jacqmin-Gadda, H. (2014). Joint modelling of repeated multivariate cognitive measures and competing risks of dementia and death: a latent process and latent class approach.

Proust-Lima, C., Joly, P., Dartigues, J.-F., & Jacqmin-Gadda, H. (2009). Joint modelling of multivariate longitudinal outcomes and a time-to-event: A nonlinear latent class approach. Computational Statistics & Data Analysis, 53(4), 1142-1154. doi:10.1016/j.csda.2008.10.017

Proust-Lima, C., Séne, M., Taylor, J. M., & Jacqmin-Gadda, H. (2014). Joint latent class models for longitudinal and time-to-event data: A review. Statistical Methods in Medical Research, 23(1), 74-90. doi:10.1177/0962280212445839

Proust-Lima, C., Philipps, V., & Liquet, B. (2015) Estimation of Extended Mixed Models Using Latent Classes and Latent Processes: the R package lcmm. Technical Report


Cécile Proust-Lima

Inserm U897

146 rue Léo Saignat

33076 Bordeaux Cedex



We are interested in feed-back but can not guarantee any support.


This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 2 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.


in zip format:

in tar.gz format: HETMIXSURV_V2.0.tar.gz