On regression adjustments to experimental data

Regression adjustments are often made to experimental data. Since randomization does not justify the models, almost anything can happen. Here, we evaluate results using Neyman's non-parametric model, where each subject has two potential responses, one if treated and the other if untreated. Only...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Advances in applied mathematics Ročník 40; číslo 2; s. 180 - 193
Hlavní autor: Freedman, David A.
Médium: Journal Article
Jazyk:angličtina
Vydáno: San Diego, CA Elsevier Inc 01.02.2008
Elsevier
Témata:
Balance
Exact sciences and technology
General mathematics
General, history and biography
Intention-to-treat
Mathematics
Multiple regression
Numerical analysis
Numerical analysis. Scientific computation
Randomization
Sciences and techniques of general use
Randomization
62A01
Models
Balance
62J99
Multiple regression
Intention-to-treat
Asymptotic expansion
Error estimation
Applied mathematics
62J99. Models
ISSN:0196-8858, 1090-2074
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Regression adjustments are often made to experimental data. Since randomization does not justify the models, almost anything can happen. Here, we evaluate results using Neyman's non-parametric model, where each subject has two potential responses, one if treated and the other if untreated. Only one of the two responses is observed. Regression estimates are generally biased, but the bias is small with large samples. Adjustment may improve precision, or make precision worse; standard errors computed according to usual procedures may overstate the precision, or understate, by quite large factors. Asymptotic expansions make these ideas more precise.
Bibliografie:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0196-8858
1090-2074
DOI:10.1016/j.aam.2006.12.003