1. |
The Fate Worse than Death and other Curiosities and Stupidities |
|
The American Statistician,
Volume 43,
Issue 3,
1989,
Page 133-134
Oscar Kempthorne,
Preview
|
PDF (165KB)
|
|
ISSN:0003-1305
DOI:10.1080/00031305.1989.10475640
出版商:Taylor & Francis Group
年代:1989
数据来源: Taylor
|
2. |
Lack-of-Fit Testing When Replicates are Not Available |
|
The American Statistician,
Volume 43,
Issue 3,
1989,
Page 135-143
G. Joglekar,
J.H. Schuenemeyer,
V. Lariccia,
Preview
|
PDF (982KB)
|
|
摘要:
The process of determining the adequacy of the fitted model is referred to as testing for lack of fit. When replicate measurements are not available, there are several approaches to testing for lack of fit. This article presents some of these approaches on a continuum so as to provide a basis for a meaningful comparison. The issue of grouping data is also discussed. A usual approach of forming groups by arbitrary cutoffs in the space of predictor variables is questioned, and a data-splitting algorithm is recommended for separating groups.
ISSN:0003-1305
DOI:10.1080/00031305.1989.10475641
出版商:Taylor & Francis Group
年代:1989
数据来源: Taylor
|
3. |
Evaluating Goodness of Fit of Poisson Regression Models in Cohort Studies |
|
The American Statistician,
Volume 43,
Issue 3,
1989,
Page 144-147
EdwardL. Frome,
MaxD. Morris,
Preview
|
PDF (444KB)
|
|
摘要:
Relative and absolute risk models are often used in epidemiologic studies to describe the effect of exposure on age-specific mortality rates. Poisson regression analysis is used to obtain maximum likelihood estimates of unknown parameters and to assess goodness of fit of the models. It is common practice to base both estimation and the evaluation of goodness of fit on certain marginal totals. This approach is potentially misleading for relative risk models and is totally inappropriate for absolute risk models. To illustrate the situation, we present an example using data on smoking and lung cancer. In the example, the goodness-of-fit tests based on the marginal totals indicate that neither the absolute risk nor the relative risk model can be rejected, whereas the age-specific test statistics strongly reject both models. The validity of the marginal test is based on an assumption (i.e., of no exposure by age interaction) that is not satisfied in the example. We describe a more general approach to model evaluation that provides the analyst with summary information for various models of interest and provides guidance on how to identify good descriptive models.
ISSN:0003-1305
DOI:10.1080/00031305.1989.10475642
出版商:Taylor & Francis Group
年代:1989
数据来源: Taylor
|
4. |
Unconditional Asymptotic Results for Simple Linear Regression |
|
The American Statistician,
Volume 43,
Issue 3,
1989,
Page 148-152
WalterN. Thurman,
Preview
|
PDF (484KB)
|
|
ISSN:0003-1305
DOI:10.1080/00031305.1989.10475643
出版商:Taylor & Francis Group
年代:1989
数据来源: Taylor
|
5. |
The Equality of the Ordinary Least Squares Estimator and the Best Linear Unbiased Estimator |
|
The American Statistician,
Volume 43,
Issue 3,
1989,
Page 153-161
Simo Puntanen,
GeorgeP. H. Styan,
Preview
|
PDF (966KB)
|
|
摘要:
It is well known that the ordinary least squares estimator ofXβin the general linear modelEy=Xβ, covy= σ2V, can be the best linear unbiased estimator even ifVis not a multiple of the identity matrix. This article presents, in a historical perspective, the development of the several conditions for the ordinary least squares estimator to be best linear unbiased. Various characterizations of these conditions, using generalized inverses and orthogonal projectors, along with several examples, are also given. In addition, a complete set of references is provided.
ISSN:0003-1305
DOI:10.1080/00031305.1989.10475644
出版商:Taylor & Francis Group
年代:1989
数据来源: Taylor
|
6. |
Comment |
|
The American Statistician,
Volume 43,
Issue 3,
1989,
Page 161-162
Oscar Kempthorne,
Preview
|
PDF (229KB)
|
|
ISSN:0003-1305
DOI:10.1080/00031305.1989.10475645
出版商:Taylor & Francis Group
年代:1989
数据来源: Taylor
|
7. |
Comment |
|
The American Statistician,
Volume 43,
Issue 3,
1989,
Page 162-163
ShayleR. Searle,
Preview
|
PDF (196KB)
|
|
ISSN:0003-1305
DOI:10.1080/00031305.1989.10475646
出版商:Taylor & Francis Group
年代:1989
数据来源: Taylor
|
8. |
Reply |
|
The American Statistician,
Volume 43,
Issue 3,
1989,
Page 164-164
Simo Puntanen,
GeorgeP. H. Styan,
Preview
|
PDF (129KB)
|
|
ISSN:0003-1305
DOI:10.1080/00031305.1989.10475647
出版商:Taylor & Francis Group
年代:1989
数据来源: Taylor
|
9. |
Analysis by Computer of Designed Experiments with Zero Degrees of Freedom for Error Variance |
|
The American Statistician,
Volume 43,
Issue 3,
1989,
Page 165-168
WilliamH. Collins,
CarolB. Collins,
Preview
|
PDF (397KB)
|
|
摘要:
Some statistical software refuses to perform regression and analysis of variance on data sets whose models allow no degrees of freedom for error variance. A related problem is getting statistical software to use a particular value for mean squared error for significance tests. We show how an external estimate of error variance can be entered via fake data in designed experiments so that the software works and the effects studied are not changed.
ISSN:0003-1305
DOI:10.1080/00031305.1989.10475648
出版商:Taylor & Francis Group
年代:1989
数据来源: Taylor
|
10. |
Computer Selection of Size-Biased Samples |
|
The American Statistician,
Volume 43,
Issue 3,
1989,
Page 168-171
DavidR. Fox,
Preview
|
PDF (373KB)
|
|
摘要:
This article describes a method for producing size-biased probability samples as originally proposed by Hanurav (1967) and Vijayan (1968). The complexity of the procedure has led to the development of microcomputer software that greatly facilitates the production of sampling plans as well as the computation of population estimates.
ISSN:0003-1305
DOI:10.1080/00031305.1989.10475649
出版商:Taylor & Francis Group
年代:1989
数据来源: Taylor
|