@article{fdi:010063674,
  title = {{A}re all species necessary to reveal ecologically important patterns ?},
  author = {{P}os, {E}. and {A}ndino, {J}. {E}. {G}. and {S}abatier, {D}aniel and {M}olino, {J}ean-{F}ran{\c{c}}ois and {P}itman, {N}. and {M}ogollon, {H}. and {N}eill, {D}. and {C}eron, {C}. and {R}ivas, {G}. and {D}i {F}iore, {A}. and {T}homas, {R}. and {T}irado, {M}. and {Y}oung, {K}. {R}. and {W}ang, {O}. and {S}ierra, {R}. and {G}arcia-{V}illacorta, {R}. and {Z}agt, {R}. and {P}alacios, {W}. and {A}ulestia, {M}. and {T}er {S}teege, {H}.},
  editor = {},
  language = {{ENG}},
  abstract = {{W}hile studying ecological patterns at large scales, ecologists are often unable to identify all collections, forcing them to either omit these unidentified records entirely, without knowing the effect of this, or pursue very costly and time-consuming efforts for identifying them. {T}hese indets may be of critical importance, but as yet, their impact on the reliability of ecological analyses is poorly known. {W}e investigated the consequence of omitting the unidentified records and provide an explanation for the results. {W}e used three large-scale independent datasets, ({G}uyana/ {S}uriname, {F}rench {G}uiana, {E}cuador) each consisting of records having been identified to a valid species name (identified morpho-species - {IMS}) and a number of unidentified records (unidentified morpho-species - {UMS}). {A} subset was created for each dataset containing only the {IMS}, which was compared with the complete dataset containing all morpho-species ({AMS}:={IMS}+{UMS}) for the following analyses: species diversity ({F}isher's alpha), similarity of species composition, {M}antel test and ordination ({NMDS}). {I}n addition, we also simulated an even larger number of unidentified records for all three datasets and analyzed the agreement between similarities again with these simulated datasets. {F}or all analyses, results were extremely similar when using the complete datasets or the truncated subsets. {IMS} predicted 91% of the variation in {AMS} in all tests/analyses. {E}ven when simulating a larger fraction of {UMS}, {IMS} predicted the results for {AMS} rather well. {U}sing only {IMS} also out-performed using higher taxon data (genus-level identification) for similarity analyses. {F}inding a high congruence for all analyses when using {IMS} rather than {AMS} suggests that patterns of similarity and composition are very robust. {I}n other words, having a large number of unidentified species in a dataset may not affect our conclusions as much as is often thought.},
  keywords = {{B}eta-diversity ; {F}isher's alpha ; indets ; large-scale ecological patterns ; {M}antel test ; morpho-species ; nonmetric multidimensional scaling ; similarity of species composition ; spatial turnover ; {GUYANA} ; {SURINAME} ; {GUYANE} {FRANCAISE} ; {EQUATEUR}},
  booktitle = {},
  journal = {{E}cology and {E}volution},
  volume = {4},
  numero = {24},
  pages = {4626--4636},
  ISSN = {2045-7758},
  year = {2014},
  DOI = {10.1002/ece3.1246},
  URL = {https://www.documentation.ird.fr/hor/fdi:010063674},
}