@article{fdi:010071344,
  title = {{P}redicting local malaria exposure using a {L}asso-based two-level cross validation algorithm},
  author = {{K}ouwaye, {B}. and {R}ossi, {F}. and {F}onton, {N}. and {G}arcia, {A}ndr{\'e} and {D}ossou-{G}b{\'e}t{\'e}, {S}. and {H}ounkonnou, {M}. {N}. and {C}ottrell, {G}illes},
  editor = {},
  language = {{ENG}},
  abstract = {{R}ecent studies have highlighted the importance of local environmental factors to determine the fine-scale heterogeneity of malaria transmission and exposure to the vector. {I}n this work, we compare a classical {GLM} model with backward selection with different versions of an automatic {LASSO}-based algorithm with 2-level cross-validation aiming to build a predictive model of the space and time dependent individual exposure to the malaria vector, using entomological and environmental data from a cohort study in {B}enin. {A}lthough the {GLM} can outperform the {LASSO} model with appropriate engineering, the best model in terms of predictive power was found to be the {LASSO}-based model. {O}ur approach can be adapted to different topics and may therefore be helpful to address prediction issues in other health sciences domains.},
  keywords = {{BENIN}},
  booktitle = {},
  journal = {{PLOS} {O}ne},
  volume = {12},
  numero = {10},
  pages = {e0187234 [14 p.]},
  ISSN = {1932-6203},
  year = {2017},
  DOI = {10.1371/journal.pone.0187234},
  URL = {https://www.documentation.ird.fr/hor/fdi:010071344},
}