Inference from randomized (factorial) experiments

Rosemary Anne Bailey

doi:10.1214/16-STS600

Inference from randomized (factorial) experiments

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

Abstract

This is a contribution to the discussion of the interesting paper by Ding [Statist. Sci. 32 (2017) 331–345], which contrasts approaches attributed to Neyman and Fisher. I believe that Fisher’s usual assumption was unit-treatment additivity, rather than the “sharp null hypothesis” attributed to him. Fisher also developed the notion of interaction in factorial experiments. His explanation leads directly to the concept of marginality, which is essential for the interpretation of data from any factorial experiment.

Original language	English
Pages (from-to)	352-355
Number of pages	4
Journal	Statistical Science
Volume	32
Issue number	3
Early online date	1 Sept 2017
DOIs	https://doi.org/10.1214/16-STS600
Publication status	Published - 2017

Keywords

Factorial design
Marginality
Randomization
Unit-treatment additivity

Access to Document

10.1214/16-STS600

Bailey-2017-Inference-STS-352
© 2017, Institute of Mathematical Statistics. This work has been made available online in accordance with the publisher’s policies. This is the final published version of the work, which was originally published at www.projecteuclid.org / https://doi.org/10.1214/16-STS600
Final published version, 97.8 KB

Cite this

@article{ce9530961f7041b380d6fc5df4d83f83,

title = "Inference from randomized (factorial) experiments",

abstract = "This is a contribution to the discussion of the interesting paper by Ding [Statist. Sci. 32 (2017) 331–345], which contrasts approaches attributed to Neyman and Fisher. I believe that Fisher{\textquoteright}s usual assumption was unit-treatment additivity, rather than the “sharp null hypothesis” attributed to him. Fisher also developed the notion of interaction in factorial experiments. His explanation leads directly to the concept of marginality, which is essential for the interpretation of data from any factorial experiment.",

keywords = "Factorial design, Marginality, Randomization, Unit-treatment additivity",

author = "Bailey, {Rosemary Anne}",

year = "2017",

doi = "10.1214/16-STS600",

language = "English",

volume = "32",

pages = "352--355",

journal = "Statistical Science",

issn = "0883-4237",

publisher = "Institute of Mathematical Statistics",

number = "3",

}

TY - JOUR

T1 - Inference from randomized (factorial) experiments

AU - Bailey, Rosemary Anne

PY - 2017

Y1 - 2017

N2 - This is a contribution to the discussion of the interesting paper by Ding [Statist. Sci. 32 (2017) 331–345], which contrasts approaches attributed to Neyman and Fisher. I believe that Fisher’s usual assumption was unit-treatment additivity, rather than the “sharp null hypothesis” attributed to him. Fisher also developed the notion of interaction in factorial experiments. His explanation leads directly to the concept of marginality, which is essential for the interpretation of data from any factorial experiment.

AB - This is a contribution to the discussion of the interesting paper by Ding [Statist. Sci. 32 (2017) 331–345], which contrasts approaches attributed to Neyman and Fisher. I believe that Fisher’s usual assumption was unit-treatment additivity, rather than the “sharp null hypothesis” attributed to him. Fisher also developed the notion of interaction in factorial experiments. His explanation leads directly to the concept of marginality, which is essential for the interpretation of data from any factorial experiment.

KW - Factorial design

KW - Marginality

KW - Randomization

KW - Unit-treatment additivity

U2 - 10.1214/16-STS600

DO - 10.1214/16-STS600

M3 - Article

SN - 0883-4237

VL - 32

SP - 352

EP - 355

JO - Statistical Science

JF - Statistical Science

IS - 3

ER -

Inference from randomized (factorial) experiments

Abstract

Keywords

Access to Document

Fingerprint

Cite this