Ecological data can be difficult to collect, and as a
result, some important temporal ecological datasets
contain irregularly sampled data. Since many temporal
modelling techniques require regularly spaced data, one
common approach is to linearly interpolate the data,
and build a model from the interpolated data. However,
this process introduces an unquantified risk that the
data is over-fitted to the interpolated (and hence more
typical) instances. Using one such irregularly-sampled
dataset, the Lake Kasumigaura algal dataset, we compare
models built on the original sample data, and on the
interpolated data, to evaluate the risk of mis-fitting
based on the interpolated data.
%0 Journal Article
%1 McKay:2006:EI
%A McKay, R. I. (Bob)
%A Hao, Hoang Tuan
%A Mori, Naoki
%A Hoai, Nguyen Xuan
%A Essam, Daryl
%D 2006
%J Ecological Informics
%K Linear Modelling algorithms, genetic interpolation, programming,
%N 3
%P 259--268
%R doi:10.1016/j.ecoinf.2006.02.005
%T Model-building with interpolated temporal data
%V 1
%X Ecological data can be difficult to collect, and as a
result, some important temporal ecological datasets
contain irregularly sampled data. Since many temporal
modelling techniques require regularly spaced data, one
common approach is to linearly interpolate the data,
and build a model from the interpolated data. However,
this process introduces an unquantified risk that the
data is over-fitted to the interpolated (and hence more
typical) instances. Using one such irregularly-sampled
dataset, the Lake Kasumigaura algal dataset, we compare
models built on the original sample data, and on the
interpolated data, to evaluate the risk of mis-fitting
based on the interpolated data.
@article{McKay:2006:EI,
abstract = {Ecological data can be difficult to collect, and as a
result, some important temporal ecological datasets
contain irregularly sampled data. Since many temporal
modelling techniques require regularly spaced data, one
common approach is to linearly interpolate the data,
and build a model from the interpolated data. However,
this process introduces an unquantified risk that the
data is over-fitted to the interpolated (and hence more
typical) instances. Using one such irregularly-sampled
dataset, the Lake Kasumigaura algal dataset, we compare
models built on the original sample data, and on the
interpolated data, to evaluate the risk of mis-fitting
based on the interpolated data.},
added-at = {2008-06-19T17:35:00.000+0200},
author = {McKay, R. I. (Bob) and Hao, Hoang Tuan and Mori, Naoki and Hoai, Nguyen Xuan and Essam, Daryl},
biburl = {https://www.bibsonomy.org/bibtex/280852f87df2fc4dfca182bcad36120f6/brazovayeye},
doi = {doi:10.1016/j.ecoinf.2006.02.005},
interhash = {3b5e5fe61a87c70bfab74f517bc8682a},
intrahash = {80852f87df2fc4dfca182bcad36120f6},
issn = {1574-9541},
journal = {Ecological Informics},
keywords = {Linear Modelling algorithms, genetic interpolation, programming,},
month = {November},
note = {4th International Conference on Ecological
Informatics},
notes = {http://www.sciencedirect.com/science/journal/15749541},
number = 3,
pages = {259--268},
timestamp = {2008-06-19T17:46:43.000+0200},
title = {Model-building with interpolated temporal data},
volume = 1,
year = 2006
}