On Extrapolating Past the Range of Observed Data When Making Statistical Predictions in Ecology.
Ecologists are increasingly using statistical models to predict animal abundance and occurrence in unsampled locations. The reliability of such predictions depends on a number of factors, including sample size, how far prediction locations are from the observed data, and similarity of predictive cov...
Published in: | PLOS ONE |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Public Library of Science (PLoS)
2015
|
Subjects: | |
Online Access: | https://doi.org/10.1371/journal.pone.0141416 https://doaj.org/article/162514be4a3b4c59b40119951565a27f |
id |
ftdoajarticles:oai:doaj.org/article:162514be4a3b4c59b40119951565a27f |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:162514be4a3b4c59b40119951565a27f 2023-05-15T15:43:52+02:00 On Extrapolating Past the Range of Observed Data When Making Statistical Predictions in Ecology. Paul B Conn Devin S Johnson Peter L Boveng 2015-01-01T00:00:00Z https://doi.org/10.1371/journal.pone.0141416 https://doaj.org/article/162514be4a3b4c59b40119951565a27f EN eng Public Library of Science (PLoS) http://europepmc.org/articles/PMC4619888?pdf=render https://doaj.org/toc/1932-6203 1932-6203 doi:10.1371/journal.pone.0141416 https://doaj.org/article/162514be4a3b4c59b40119951565a27f PLoS ONE, Vol 10, Iss 10, p e0141416 (2015) Medicine R Science Q article 2015 ftdoajarticles https://doi.org/10.1371/journal.pone.0141416 2022-12-31T01:25:28Z Ecologists are increasingly using statistical models to predict animal abundance and occurrence in unsampled locations. The reliability of such predictions depends on a number of factors, including sample size, how far prediction locations are from the observed data, and similarity of predictive covariates in locations where data are gathered to locations where predictions are desired. In this paper, we propose extending Cook's notion of an independent variable hull (IVH), developed originally for application with linear regression models, to generalized regression models as a way to help assess the potential reliability of predictions in unsampled areas. Predictions occurring inside the generalized independent variable hull (gIVH) can be regarded as interpolations, while predictions occurring outside the gIVH can be regarded as extrapolations worthy of additional investigation or skepticism. We conduct a simulation study to demonstrate the usefulness of this metric for limiting the scope of spatial inference when conducting model-based abundance estimation from survey counts. In this case, limiting inference to the gIVH substantially reduces bias, especially when survey designs are spatially imbalanced. We also demonstrate the utility of the gIVH in diagnosing problematic extrapolations when estimating the relative abundance of ribbon seals in the Bering Sea as a function of predictive covariates. We suggest that ecologists routinely use diagnostics such as the gIVH to help gauge the reliability of predictions from statistical models (such as generalized linear, generalized additive, and spatio-temporal regression models). Article in Journal/Newspaper Bering Sea Directory of Open Access Journals: DOAJ Articles Bering Sea PLOS ONE 10 10 e0141416 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Medicine R Science Q |
spellingShingle |
Medicine R Science Q Paul B Conn Devin S Johnson Peter L Boveng On Extrapolating Past the Range of Observed Data When Making Statistical Predictions in Ecology. |
topic_facet |
Medicine R Science Q |
description |
Ecologists are increasingly using statistical models to predict animal abundance and occurrence in unsampled locations. The reliability of such predictions depends on a number of factors, including sample size, how far prediction locations are from the observed data, and similarity of predictive covariates in locations where data are gathered to locations where predictions are desired. In this paper, we propose extending Cook's notion of an independent variable hull (IVH), developed originally for application with linear regression models, to generalized regression models as a way to help assess the potential reliability of predictions in unsampled areas. Predictions occurring inside the generalized independent variable hull (gIVH) can be regarded as interpolations, while predictions occurring outside the gIVH can be regarded as extrapolations worthy of additional investigation or skepticism. We conduct a simulation study to demonstrate the usefulness of this metric for limiting the scope of spatial inference when conducting model-based abundance estimation from survey counts. In this case, limiting inference to the gIVH substantially reduces bias, especially when survey designs are spatially imbalanced. We also demonstrate the utility of the gIVH in diagnosing problematic extrapolations when estimating the relative abundance of ribbon seals in the Bering Sea as a function of predictive covariates. We suggest that ecologists routinely use diagnostics such as the gIVH to help gauge the reliability of predictions from statistical models (such as generalized linear, generalized additive, and spatio-temporal regression models). |
format |
Article in Journal/Newspaper |
author |
Paul B Conn Devin S Johnson Peter L Boveng |
author_facet |
Paul B Conn Devin S Johnson Peter L Boveng |
author_sort |
Paul B Conn |
title |
On Extrapolating Past the Range of Observed Data When Making Statistical Predictions in Ecology. |
title_short |
On Extrapolating Past the Range of Observed Data When Making Statistical Predictions in Ecology. |
title_full |
On Extrapolating Past the Range of Observed Data When Making Statistical Predictions in Ecology. |
title_fullStr |
On Extrapolating Past the Range of Observed Data When Making Statistical Predictions in Ecology. |
title_full_unstemmed |
On Extrapolating Past the Range of Observed Data When Making Statistical Predictions in Ecology. |
title_sort |
on extrapolating past the range of observed data when making statistical predictions in ecology. |
publisher |
Public Library of Science (PLoS) |
publishDate |
2015 |
url |
https://doi.org/10.1371/journal.pone.0141416 https://doaj.org/article/162514be4a3b4c59b40119951565a27f |
geographic |
Bering Sea |
geographic_facet |
Bering Sea |
genre |
Bering Sea |
genre_facet |
Bering Sea |
op_source |
PLoS ONE, Vol 10, Iss 10, p e0141416 (2015) |
op_relation |
http://europepmc.org/articles/PMC4619888?pdf=render https://doaj.org/toc/1932-6203 1932-6203 doi:10.1371/journal.pone.0141416 https://doaj.org/article/162514be4a3b4c59b40119951565a27f |
op_doi |
https://doi.org/10.1371/journal.pone.0141416 |
container_title |
PLOS ONE |
container_volume |
10 |
container_issue |
10 |
container_start_page |
e0141416 |
_version_ |
1766378084928323584 |