|
1. |
Follow-Up Designs to Resolve Confounding in Multifactor Experiments |
|
Technometrics,
Volume 38,
Issue 4,
1996,
Page 303-313
R.Daniel Meyer,
DavidM. Steinberg,
George Box,
Preview
|
PDF (1343KB)
|
|
摘要:
Fractional factorial, Plackett-Burman, and other multifactor designs are often effective in practice due to factor sparsity. That is, just a few of the many factors studied will have major effects. In those active factors, these designs can have high resolution. We have previously developed a Bayesian method based on the idea of model discrimination that uncovers the active factors. Sometimes, the results of a fractional experiment are ambiguous due to confounding among the possible effects, and more than one model may be consistent with the data. Within the Bayesian construct, we have developed a method for designing a follow-up experiment to resolve this ambiguity. The idea is to choose runs that allow maximum discrimination among the plausible models. This method is more general than methods that algebraically decouple aliased interactions and more appropriate than optimal design methods that require specification of a single model. The method is illustrated through examples of fractional experiments.
ISSN:0040-1706
DOI:10.1080/00401706.1996.10484538
出版商:Taylor & Francis Group
年代:1996
数据来源: Taylor
|
2. |
Discussion: Posterior Probabilities and Experimental Designs for Discriminating Between Regression Models |
|
Technometrics,
Volume 38,
Issue 4,
1996,
Page 314-317
A.C. Atkinson,
Preview
|
PDF (524KB)
|
|
ISSN:0040-1706
DOI:10.1080/00401706.1996.10484539
出版商:Taylor & Francis Group
年代:1996
数据来源: Taylor
|
3. |
Discussion: Factor-Based or Effect-Based Modeling? Implications for Design |
|
Technometrics,
Volume 38,
Issue 4,
1996,
Page 317-320
HughA. Chipman,
MichaelS. Hamada,
Preview
|
PDF (504KB)
|
|
ISSN:0040-1706
DOI:10.1080/00401706.1996.10484540
出版商:Taylor & Francis Group
年代:1996
数据来源: Taylor
|
4. |
Discussion |
|
Technometrics,
Volume 38,
Issue 4,
1996,
Page 321-322
Valerii Fedorov,
Preview
|
PDF (207KB)
|
|
ISSN:0040-1706
DOI:10.1080/00401706.1996.10484541
出版商:Taylor & Francis Group
年代:1996
数据来源: Taylor
|
5. |
Discussion |
|
Technometrics,
Volume 38,
Issue 4,
1996,
Page 323-326
Bradley Jones,
William Dumouchel,
Preview
|
PDF (476KB)
|
|
ISSN:0040-1706
DOI:10.1080/00401706.1996.10484542
出版商:Taylor & Francis Group
年代:1996
数据来源: Taylor
|
6. |
Discussion |
|
Technometrics,
Volume 38,
Issue 4,
1996,
Page 326-327
RandallD. Tobias,
Preview
|
PDF (245KB)
|
|
ISSN:0040-1706
DOI:10.1080/00401706.1996.10484543
出版商:Taylor & Francis Group
年代:1996
数据来源: Taylor
|
7. |
Reply |
|
Technometrics,
Volume 38,
Issue 4,
1996,
Page 327-332
R.Daniel Meyer,
DavidS. Steinberg,
George Box,
Preview
|
PDF (771KB)
|
|
ISSN:0040-1706
DOI:10.1080/00401706.1996.10484544
出版商:Taylor & Francis Group
年代:1996
数据来源: Taylor
|
8. |
Experimental Designs Optimally Balanced for Trend |
|
Technometrics,
Volume 38,
Issue 4,
1996,
Page 333-341
A.C. Atkinson,
A.N. Donev,
Preview
|
PDF (1023KB)
|
|
摘要:
When experiments are carried out over a period of time, the response may be subject to time trends. We use an algorithm for exact optimum designs to construct a series of designs resistant to linear and quadratic trend. Designs considered include the allocation of simple treatments, multifactor designs in qualitative or quantitative factors, and response surface designs. The investigation is extended from consideration of linear ordering in time to include designs with several trials at each time point, designs in which several trials are spread over only one out of three shifts per day, and designs in which there are more time points than experiments. Comparisons with designs in the absence of trend show that surprisingly little information is lost by designing for protection against a potential trend. The BT algorithm for obtaining these designs is outlined.
ISSN:0040-1706
DOI:10.1080/00401706.1996.10484545
出版商:Taylor & Francis Group
年代:1996
数据来源: Taylor
|
9. |
Construction of Orthogonal Two-Level Designs of User-Specified Resolution WhereN≠ 2k |
|
Technometrics,
Volume 38,
Issue 4,
1996,
Page 342-353
C.T. Liao,
H.K. Iyer,
D.F. Vecchia,
Preview
|
PDF (1324KB)
|
|
摘要:
Fractional two-level factorial designs are often used in the early stages of an investigation to screen for important factors. Traditionally, 2n-kfractional factorial designs of resolution III, IV, or V have been used for this purpose. When the investigator is able to specify the set of nonnegligible factorial effects, it is sometimes possible to obtain an orthogonal design with fewer runs than a standard textbook design by searching within a wider class of designs called parallel-flats designs. The run sizes in this class of designs do not necessarily need to be powers of 2. We discuss an algorithm for constructing orthogonal parallel-flats designs to meet user specifications. Several examples illustrate the use of the algorithm.
ISSN:0040-1706
DOI:10.1080/00401706.1996.10484546
出版商:Taylor & Francis Group
年代:1996
数据来源: Taylor
|
10. |
Some Useful Compound Dispersion Experiments in Quality Design |
|
Technometrics,
Volume 38,
Issue 4,
1996,
Page 354-364
PaulR. Rosenbaum,
Preview
|
PDF (1181KB)
|
|
摘要:
Dispersion experiments examine the effects of control factors on dispersion introduced by error factors. Error factors can be controlled in the laboratory but cannot be controlled when a product is used. For dispersion experiments, Taguchi used direct product designs in which control-factor levels are set by one orthogonal array, error-factor levels are set by another orthogonal array, and, for each combination of control-factor and error-factor levels, an observation is taken. In contrast, compound designs, which include product designs as special cases, share several of the attractive properties of Taguchi's designs, but they are often smaller for a given strength, or stronger for a given size, where strength refers to strength of the orthogonal array. This article discusses several useful compound designs for dispersion experiments and several general methods for constructing such designs. In particular, compound designs can be built from existing tabulations of confounded factorial designs.
ISSN:0040-1706
DOI:10.1080/00401706.1996.10484547
出版商:Taylor & Francis Group
年代:1996
数据来源: Taylor
|
|