@article{fdi:010064470,
  title = {{A}n alternative classification to mixture modeling for longitudinal counts or binary measures},
  author = {{S}ubtil, {F}. and {B}oussari, {O}. and {B}astard, {M}. and {E}tard, {J}ean-{F}ran{\c{c}}ois and {E}cochard, {R}. and {G}{\'e}nolini, {C}.},
  editor = {},
  language = {{ENG}},
  abstract = {{C}lassifying patients according to longitudinal measures, or trajectory classification, has become frequent in clinical research. {T}he k-means algorithm is increasingly used for this task in case of continuous variables with standard deviations that do not depend on the mean. {O}ne feature of count and binary data modeled by {P}oisson or logistic regression is that the variance depends on the mean; hence, the within-group variability changes from one group to another depending on the mean trajectory level. {M}ixture modeling could be used here for classification though its main purpose is to model the data. {T}he results obtained may change according to the main objective. {T}his article presents an extension of the k-means algorithm that takes into account the features of count and binary data by using the deviance as distance metric. {T}his approach is justified by its analogy with the classification likelihood. {T}wo applications are presented with binary and count data to show the differences between the classifications obtained with the usual {E}uclidean distance versus the deviance distance.},
  keywords = {{SANTE} ; {METHODE} {D}'{ANALYSE} ; {ANALYSE} {STATISTIQUE} ; {ALGORITHME} ; {ETUDE} {DE} {CAS} ; {PALUDISME} ; {MOUSTIQUE} ; {ANALYSE} {QUANTITATIVE} ; {SIDA} ; {TRAITEMENT} {MEDICAL} ; {MEDICAMENT} ; {ITINERAIRE} {THERAPEUTIQUE} ; {BIOSTATISTIQUE} ; {BENIN}},
  booktitle = {},
  journal = {{S}tatistical {M}ethods in {M}edical {R}esearch},
  volume = {26},
  numero = {1},
  pages = {453--470},
  ISSN = {0962-2802},
  year = {2017},
  DOI = {10.1177/0962280214549040},
  URL = {https://www.documentation.ird.fr/hor/fdi:010064470},
}