Bivariate Downscaling With Asynchronous Measurements

Xuming He, Yunwen Yang, Jingfei Zhang

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Statistical downscaling is a useful technique to localize global or regional climate model projections to assess the potential impact of climate changes. It requires quantifying a relationship between climate model output and local observations from the past, but the two sets of measurements are not necessarily taken simultaneously, so the usual regression techniques are not applicable. In the case of univariate downscaling, the Statistical Asynchronous Regression (SAR) method of O'Brien, Sornette, and McPherron (Journal of Geophysical Research, 106, 13247-13259, 2001) provides a simple quantile-matching approach with asynchronous measurements. In this paper, we propose a bivariate downscaling method for asynchronous measurements based on a notion of bivariate ranks and positions. The proposed method is preferable to univariate downscaling, because it is able to preserve general forms of association between two variables, such as temperature and precipitation, in statistical downscaling. This desirable property of the bivariate downscaling method is demonstrated through applications to simulated and real data.

Original languageEnglish (US)
Pages (from-to)476-489
Number of pages14
JournalJournal of Agricultural, Biological, and Environmental Statistics
Volume17
Issue number3
DOIs
StatePublished - Sep 1 2012
Externally publishedYes

Fingerprint

downscaling
Climate models
Climate Models
Climate
Univariate
Regression
climate models
Climate change
Climate Change
climate modeling
Quantile
methodology
Regression Analysis
Projection
regional climate
Temperature
preserves
global climate
Output
regression analysis

Keywords

  • Asynchronous regression
  • Bivariate ranks
  • Climate
  • Quantile
  • Statistical downscaling

ASJC Scopus subject areas

  • Agricultural and Biological Sciences(all)
  • Environmental Science(all)
  • Agricultural and Biological Sciences (miscellaneous)
  • Applied Mathematics
  • Statistics, Probability and Uncertainty
  • Statistics and Probability

Cite this

Bivariate Downscaling With Asynchronous Measurements. / He, Xuming; Yang, Yunwen; Zhang, Jingfei.

In: Journal of Agricultural, Biological, and Environmental Statistics, Vol. 17, No. 3, 01.09.2012, p. 476-489.

Research output: Contribution to journalArticle

@article{0b21f74ca8164f3c8726a24cc8e72829,
title = "Bivariate Downscaling With Asynchronous Measurements",
abstract = "Statistical downscaling is a useful technique to localize global or regional climate model projections to assess the potential impact of climate changes. It requires quantifying a relationship between climate model output and local observations from the past, but the two sets of measurements are not necessarily taken simultaneously, so the usual regression techniques are not applicable. In the case of univariate downscaling, the Statistical Asynchronous Regression (SAR) method of O'Brien, Sornette, and McPherron (Journal of Geophysical Research, 106, 13247-13259, 2001) provides a simple quantile-matching approach with asynchronous measurements. In this paper, we propose a bivariate downscaling method for asynchronous measurements based on a notion of bivariate ranks and positions. The proposed method is preferable to univariate downscaling, because it is able to preserve general forms of association between two variables, such as temperature and precipitation, in statistical downscaling. This desirable property of the bivariate downscaling method is demonstrated through applications to simulated and real data.",
keywords = "Asynchronous regression, Bivariate ranks, Climate, Quantile, Statistical downscaling",
author = "Xuming He and Yunwen Yang and Jingfei Zhang",
year = "2012",
month = "9",
day = "1",
doi = "10.1007/s13253-012-0098-6",
language = "English (US)",
volume = "17",
pages = "476--489",
journal = "Journal of Agricultural, Biological, and Environmental Statistics",
issn = "1085-7117",
publisher = "Springer New York",
number = "3",

}

TY - JOUR

T1 - Bivariate Downscaling With Asynchronous Measurements

AU - He, Xuming

AU - Yang, Yunwen

AU - Zhang, Jingfei

PY - 2012/9/1

Y1 - 2012/9/1

N2 - Statistical downscaling is a useful technique to localize global or regional climate model projections to assess the potential impact of climate changes. It requires quantifying a relationship between climate model output and local observations from the past, but the two sets of measurements are not necessarily taken simultaneously, so the usual regression techniques are not applicable. In the case of univariate downscaling, the Statistical Asynchronous Regression (SAR) method of O'Brien, Sornette, and McPherron (Journal of Geophysical Research, 106, 13247-13259, 2001) provides a simple quantile-matching approach with asynchronous measurements. In this paper, we propose a bivariate downscaling method for asynchronous measurements based on a notion of bivariate ranks and positions. The proposed method is preferable to univariate downscaling, because it is able to preserve general forms of association between two variables, such as temperature and precipitation, in statistical downscaling. This desirable property of the bivariate downscaling method is demonstrated through applications to simulated and real data.

AB - Statistical downscaling is a useful technique to localize global or regional climate model projections to assess the potential impact of climate changes. It requires quantifying a relationship between climate model output and local observations from the past, but the two sets of measurements are not necessarily taken simultaneously, so the usual regression techniques are not applicable. In the case of univariate downscaling, the Statistical Asynchronous Regression (SAR) method of O'Brien, Sornette, and McPherron (Journal of Geophysical Research, 106, 13247-13259, 2001) provides a simple quantile-matching approach with asynchronous measurements. In this paper, we propose a bivariate downscaling method for asynchronous measurements based on a notion of bivariate ranks and positions. The proposed method is preferable to univariate downscaling, because it is able to preserve general forms of association between two variables, such as temperature and precipitation, in statistical downscaling. This desirable property of the bivariate downscaling method is demonstrated through applications to simulated and real data.

KW - Asynchronous regression

KW - Bivariate ranks

KW - Climate

KW - Quantile

KW - Statistical downscaling

UR - http://www.scopus.com/inward/record.url?scp=84866740056&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866740056&partnerID=8YFLogxK

U2 - 10.1007/s13253-012-0098-6

DO - 10.1007/s13253-012-0098-6

M3 - Article

AN - SCOPUS:84866740056

VL - 17

SP - 476

EP - 489

JO - Journal of Agricultural, Biological, and Environmental Statistics

JF - Journal of Agricultural, Biological, and Environmental Statistics

SN - 1085-7117

IS - 3

ER -