A simple approach for finding estimable functions in linear models

R. K. Elswick; Chris Gennings; Vernon Chinchilli; Kathryn S. Dawson

doi:10.1080/00031305.1991.10475766

A simple approach for finding estimable functions in linear models

R. K. Elswick, Chris Gennings, Vernon Chinchilli, Kathryn S. Dawson

Research output: Contribution to journal › Article › peer-review

7 Scopus citations

Abstract

In some overparameterized linear models it can be difficult to determine which parametric functions are estimable. Students in linear models courses and data analysts usually rely upon intuition and/or trial and error methods to determine estimability. We suggest reducing the design matrix to row echelon form as a means of finding the structure of all estimable functions. We illustrate the procedure with two examples.

Original language	English (US)
Pages (from-to)	51-53
Number of pages	3
Journal	American Statistician
Volume	45
Issue number	1
DOIs	https://doi.org/10.1080/00031305.1991.10475766
State	Published - Feb 1991

All Science Journal Classification (ASJC) codes

Statistics and Probability
General Mathematics
Statistics, Probability and Uncertainty

Access to Document

10.1080/00031305.1991.10475766

Cite this

@article{6703e4f315f84b83ba7655e5c6db32b3,

title = "A simple approach for finding estimable functions in linear models",

abstract = "In some overparameterized linear models it can be difficult to determine which parametric functions are estimable. Students in linear models courses and data analysts usually rely upon intuition and/or trial and error methods to determine estimability. We suggest reducing the design matrix to row echelon form as a means of finding the structure of all estimable functions. We illustrate the procedure with two examples.",

author = "Elswick, {R. K.} and Chris Gennings and Vernon Chinchilli and Dawson, {Kathryn S.}",

year = "1991",

month = feb,

doi = "10.1080/00031305.1991.10475766",

language = "English (US)",

volume = "45",

pages = "51--53",

journal = "American Statistician",

issn = "0003-1305",

publisher = "Taylor and Francis Ltd.",

number = "1",

}

TY - JOUR

T1 - A simple approach for finding estimable functions in linear models

AU - Elswick, R. K.

AU - Gennings, Chris

AU - Chinchilli, Vernon

AU - Dawson, Kathryn S.

PY - 1991/2

Y1 - 1991/2

N2 - In some overparameterized linear models it can be difficult to determine which parametric functions are estimable. Students in linear models courses and data analysts usually rely upon intuition and/or trial and error methods to determine estimability. We suggest reducing the design matrix to row echelon form as a means of finding the structure of all estimable functions. We illustrate the procedure with two examples.

AB - In some overparameterized linear models it can be difficult to determine which parametric functions are estimable. Students in linear models courses and data analysts usually rely upon intuition and/or trial and error methods to determine estimability. We suggest reducing the design matrix to row echelon form as a means of finding the structure of all estimable functions. We illustrate the procedure with two examples.

UR - http://www.scopus.com/inward/record.url?scp=33749758538&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33749758538&partnerID=8YFLogxK

U2 - 10.1080/00031305.1991.10475766

DO - 10.1080/00031305.1991.10475766

M3 - Article

AN - SCOPUS:33749758538

SN - 0003-1305

VL - 45

SP - 51

EP - 53

JO - American Statistician

JF - American Statistician

IS - 1

ER -

A simple approach for finding estimable functions in linear models

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this