Abstract
Model selection and model averaging are essential to regression analysis in environmental studies, but determining which of the two approaches is the more appropriate and under what circumstances remains an active research topic. In this paper, we focus on geostatistical regression models for spatially referenced environmental data. For a general information criterion, we develop a new perturbation-based criterion that measures the uncertainty (or, instability) of spatial model selection, as well as an empirical rule for choosing between model selection and model averaging. Statistical inference based on the proposed model selection instability measure is justified both in theory and via a simulation study. The predictive performance of model selection and model averaging can be quite different when the uncertainty in model selection is relatively large, but the performance becomes more comparable as this uncertainty decreases. For illustration, a precipitation data set in the state of Colorado is analyzed.
| Original language | English |
|---|---|
| Pages (from-to) | 203-228 |
| Number of pages | 26 |
| Journal | Statistica Sinica |
| Volume | 28 |
| Issue number | 1 |
| DOIs | |
| Publication status | Published - 2018 Jan 1 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Statistics and Probability
- Statistics, Probability and Uncertainty
Cite this
}
A generalized measure of uncertainty in geostatistical model selection. / Chen, Chun-Shu; Zhu, Jun; Chu, Tingjin.
In: Statistica Sinica, Vol. 28, No. 1, 01.01.2018, p. 203-228.Research output: Contribution to journal › Review article
TY - JOUR
T1 - A generalized measure of uncertainty in geostatistical model selection
AU - Chen, Chun-Shu
AU - Zhu, Jun
AU - Chu, Tingjin
PY - 2018/1/1
Y1 - 2018/1/1
N2 - Model selection and model averaging are essential to regression analysis in environmental studies, but determining which of the two approaches is the more appropriate and under what circumstances remains an active research topic. In this paper, we focus on geostatistical regression models for spatially referenced environmental data. For a general information criterion, we develop a new perturbation-based criterion that measures the uncertainty (or, instability) of spatial model selection, as well as an empirical rule for choosing between model selection and model averaging. Statistical inference based on the proposed model selection instability measure is justified both in theory and via a simulation study. The predictive performance of model selection and model averaging can be quite different when the uncertainty in model selection is relatively large, but the performance becomes more comparable as this uncertainty decreases. For illustration, a precipitation data set in the state of Colorado is analyzed.
AB - Model selection and model averaging are essential to regression analysis in environmental studies, but determining which of the two approaches is the more appropriate and under what circumstances remains an active research topic. In this paper, we focus on geostatistical regression models for spatially referenced environmental data. For a general information criterion, we develop a new perturbation-based criterion that measures the uncertainty (or, instability) of spatial model selection, as well as an empirical rule for choosing between model selection and model averaging. Statistical inference based on the proposed model selection instability measure is justified both in theory and via a simulation study. The predictive performance of model selection and model averaging can be quite different when the uncertainty in model selection is relatively large, but the performance becomes more comparable as this uncertainty decreases. For illustration, a precipitation data set in the state of Colorado is analyzed.
UR - http://www.scopus.com/inward/record.url?scp=85040098506&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85040098506&partnerID=8YFLogxK
U2 - 10.5705/ss.202016.0368
DO - 10.5705/ss.202016.0368
M3 - Review article
AN - SCOPUS:85040098506
VL - 28
SP - 203
EP - 228
JO - Statistica Sinica
JF - Statistica Sinica
SN - 1017-0405
IS - 1
ER -