Abstract
Several frequently used estimates of the domain of a regression model are discussed and compared with the convex hull of the predictor-variable values. A simple procedure for identifying new prediction values as interpolation or extrapolation points is presented using the convex hull as the model domain estimate and is illustrated by examples.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 187-190 |
| Number of pages | 4 |
| Journal | American Statistician |
| Volume | 42 |
| Issue number | 3 |
| DOIs | |
| State | Published - 1988 |
Fingerprint
Keywords
- Convex hull
- Extrapolation
- Interpolation
- Model domain
ASJC Scopus subject areas
- Mathematics(all)
- Statistics and Probability
- Statistics, Probability and Uncertainty
Cite this
Characterizing the domain of a regression model. / Brooks, Daniel G.; Carroll, Steven S.; Verdini, William A.
In: American Statistician, Vol. 42, No. 3, 1988, p. 187-190.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Characterizing the domain of a regression model
AU - Brooks, Daniel G.
AU - Carroll, Steven S.
AU - Verdini, William A.
PY - 1988
Y1 - 1988
N2 - Several frequently used estimates of the domain of a regression model are discussed and compared with the convex hull of the predictor-variable values. A simple procedure for identifying new prediction values as interpolation or extrapolation points is presented using the convex hull as the model domain estimate and is illustrated by examples.
AB - Several frequently used estimates of the domain of a regression model are discussed and compared with the convex hull of the predictor-variable values. A simple procedure for identifying new prediction values as interpolation or extrapolation points is presented using the convex hull as the model domain estimate and is illustrated by examples.
KW - Convex hull
KW - Extrapolation
KW - Interpolation
KW - Model domain
UR - http://www.scopus.com/inward/record.url?scp=0000127755&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0000127755&partnerID=8YFLogxK
U2 - 10.1080/00031305.1988.10475559
DO - 10.1080/00031305.1988.10475559
M3 - Article
VL - 42
SP - 187
EP - 190
JO - American Statistician
JF - American Statistician
SN - 0003-1305
IS - 3
ER -