Downscaling livestock census data using multivariate predictive models: Sensitivity to modifiable areal unit problem

The analysis of census data aggregated by administrative units introduces a statistical bias known as the modifiable areal unit problem (MAUP). Previous researches have mostly assessed the effect of MAUP on upscaling models. The present study contributes to clarify the effects of MAUP on the downsca...

Full description

Bibliographic Details
Main Authors: Re, D. da, Gilbert, Marius, Chaiban, C., Bourguignon, P., Thanapongtharm, Weerapong, Robinson, Timothy P., Vanwambeke, S.O.
Format: Journal Article
Language:Inglés
Published: Public Library of Science 2020
Subjects:
Online Access:https://hdl.handle.net/10568/110662
_version_ 1855534848027918336
author Re, D. da
Gilbert, Marius
Chaiban, C.
Bourguignon, P.
Thanapongtharm, Weerapong
Robinson, Timothy P.
Vanwambeke, S.O.
author_browse Bourguignon, P.
Chaiban, C.
Gilbert, Marius
Re, D. da
Robinson, Timothy P.
Thanapongtharm, Weerapong
Vanwambeke, S.O.
author_facet Re, D. da
Gilbert, Marius
Chaiban, C.
Bourguignon, P.
Thanapongtharm, Weerapong
Robinson, Timothy P.
Vanwambeke, S.O.
author_sort Re, D. da
collection Repository of Agricultural Research Outputs (CGSpace)
description The analysis of census data aggregated by administrative units introduces a statistical bias known as the modifiable areal unit problem (MAUP). Previous researches have mostly assessed the effect of MAUP on upscaling models. The present study contributes to clarify the effects of MAUP on the downscaling methodologies, highlighting how a priori choices of scales and shapes could influence the results. We aggregated chicken and duck fine-resolution census in Thailand, using three administrative census levels in regular and irregular shapes. We then disaggregated the data within the Gridded Livestock of the World analytical framework, sampling predictors in two different ways. A sensitivity analysis on Pearson’s r correlation statistics and RMSE was carried out to understand how size and shapes of the response variables affect the goodness-of-fit and downscaling performances. We showed that scale, rather than shapes and sampling methods, affected downscaling precision, suggesting that training the model using the finest administrative level available is preferable. Moreover, datasets showing non-homogeneous distribution but instead spatial clustering seemed less affected by MAUP, yielding higher Pearson’s r values and lower RMSE compared to a more spatially homogenous dataset. Implementing aggregation sensitivity analysis in spatial studies could help to interpret complex results and disseminate robust products.
format Journal Article
id CGSpace110662
institution CGIAR Consortium
language Inglés
publishDate 2020
publishDateRange 2020
publishDateSort 2020
publisher Public Library of Science
publisherStr Public Library of Science
record_format dspace
spelling CGSpace1106622025-01-24T14:20:17Z Downscaling livestock census data using multivariate predictive models: Sensitivity to modifiable areal unit problem Re, D. da Gilbert, Marius Chaiban, C. Bourguignon, P. Thanapongtharm, Weerapong Robinson, Timothy P. Vanwambeke, S.O. livestock data censuses The analysis of census data aggregated by administrative units introduces a statistical bias known as the modifiable areal unit problem (MAUP). Previous researches have mostly assessed the effect of MAUP on upscaling models. The present study contributes to clarify the effects of MAUP on the downscaling methodologies, highlighting how a priori choices of scales and shapes could influence the results. We aggregated chicken and duck fine-resolution census in Thailand, using three administrative census levels in regular and irregular shapes. We then disaggregated the data within the Gridded Livestock of the World analytical framework, sampling predictors in two different ways. A sensitivity analysis on Pearson’s r correlation statistics and RMSE was carried out to understand how size and shapes of the response variables affect the goodness-of-fit and downscaling performances. We showed that scale, rather than shapes and sampling methods, affected downscaling precision, suggesting that training the model using the finest administrative level available is preferable. Moreover, datasets showing non-homogeneous distribution but instead spatial clustering seemed less affected by MAUP, yielding higher Pearson’s r values and lower RMSE compared to a more spatially homogenous dataset. Implementing aggregation sensitivity analysis in spatial studies could help to interpret complex results and disseminate robust products. 2020-01-27 2020-12-29T09:23:08Z 2020-12-29T09:23:08Z Journal Article https://hdl.handle.net/10568/110662 en Open Access Public Library of Science Da Re, D., Gilbert, M., Chaiban, C., Bourguignon, P., Thanapongtharm, W., Robinson, T.P. and Vanwambeke, S.O. 2020. Downscaling livestock census data using multivariate predictive models: Sensitivity to modifiable areal unit problem. PLoS ONE 15(1):e0221070.
spellingShingle livestock
data
censuses
Re, D. da
Gilbert, Marius
Chaiban, C.
Bourguignon, P.
Thanapongtharm, Weerapong
Robinson, Timothy P.
Vanwambeke, S.O.
Downscaling livestock census data using multivariate predictive models: Sensitivity to modifiable areal unit problem
title Downscaling livestock census data using multivariate predictive models: Sensitivity to modifiable areal unit problem
title_full Downscaling livestock census data using multivariate predictive models: Sensitivity to modifiable areal unit problem
title_fullStr Downscaling livestock census data using multivariate predictive models: Sensitivity to modifiable areal unit problem
title_full_unstemmed Downscaling livestock census data using multivariate predictive models: Sensitivity to modifiable areal unit problem
title_short Downscaling livestock census data using multivariate predictive models: Sensitivity to modifiable areal unit problem
title_sort downscaling livestock census data using multivariate predictive models sensitivity to modifiable areal unit problem
topic livestock
data
censuses
url https://hdl.handle.net/10568/110662
work_keys_str_mv AT redda downscalinglivestockcensusdatausingmultivariatepredictivemodelssensitivitytomodifiablearealunitproblem
AT gilbertmarius downscalinglivestockcensusdatausingmultivariatepredictivemodelssensitivitytomodifiablearealunitproblem
AT chaibanc downscalinglivestockcensusdatausingmultivariatepredictivemodelssensitivitytomodifiablearealunitproblem
AT bourguignonp downscalinglivestockcensusdatausingmultivariatepredictivemodelssensitivitytomodifiablearealunitproblem
AT thanapongtharmweerapong downscalinglivestockcensusdatausingmultivariatepredictivemodelssensitivitytomodifiablearealunitproblem
AT robinsontimothyp downscalinglivestockcensusdatausingmultivariatepredictivemodelssensitivitytomodifiablearealunitproblem
AT vanwambekeso downscalinglivestockcensusdatausingmultivariatepredictivemodelssensitivitytomodifiablearealunitproblem