Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Discovery Grants Program - Individual

University of Manitoba

$14,000.00

Design and analysis of industrial experiments

FY 2008-09

Summary
In industry, statistically designed experiments are used to improve the quality of products and processes. In screening experiments the goal is to identify the factors that have the biggest impact on quality. In robustness experiments the goal is to choose settings for the control factors to make the product or process less sensitive to uncontrolled variation (noise). Often the screening or robustness experiments have a "split-plot" structure. In some cases, this is because of the presence of hard-to-vary and easy-to-vary factors or because of constraints imposed by the equipment. In other cases, it is because the experimenter is more interested in certain effects than others. This proposal is concerned with both the design and analysis of industrial experiments, with a particular emphasis on split-plot designs. With respect to design, there are two broad objectives: the first is to develop a unifying way of thinking about optimality criteria for fractional factorial split-plot designs, with or without blocking, and to construct catalogs of optimal designs; the second is to develop optimality criteria for semi-foldover plans for fractional factorial split-plot designs, with or without blocking, and to construct catalogs of optimal plans. With respect to analysis, there are also two broad objectives. The first objective is to use the post-data pivotal approach to provide an alternative way of analyzing data that arise from split-plot experiments in industry and to extend this approach to other types of industrial experiments. The post-data pivotal approach circumvents difficulties that occur with classical inference procedures in constrained parameter space problems. For example, these difficulties include negative estimates of variance components in split-plot experiments. The second objective is to develop new ways of analyzing data arising from computer experiments with functional output.
Program
Discovery Grants Program - Individual
Location
Manitoba, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
26702-2008
Name nom
Brewster, John
Department département
Statistics
Organization id
19
Institution établissement
University of Manitoba
Province en
Manitoba
Province fr
Manitoba
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2008
Competition year année de concours
2008
Award amount
14000
Program id
RGPIN
Program nane en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
14
Committee name en
Statistical Sciences
Committee name fr
Statistique
Area of application code
1205
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Mathematical sciences
Area of application fr
Sciences mathématiques
Research subject code
3001
Research subject group en
Statistics and probability
Research subject group fr
Statistique et probabilité
Research subject en
Statistical theory
Research subject fr
Théorie de statistique
Partie
1
Nb partie
5
Application title
Design and analysis of industrial experiments
Keyword
NA
Application summary
In industry, statistically designed experiments are used to improve the quality of products and processes. In screening experiments the goal is to identify the factors that have the biggest impact on quality. In robustness experiments the goal is to choose settings for the control factors to make the product or process less sensitive to uncontrolled variation (noise). Often the screening or robustness experiments have a "split-plot" structure. In some cases, this is because of the presence of hard-to-vary and easy-to-vary factors or because of constraints imposed by the equipment. In other cases, it is because the experimenter is more interested in certain effects than others. This proposal is concerned with both the design and analysis of industrial experiments, with a particular emphasis on split-plot designs. With respect to design, there are two broad objectives: the first is to develop a unifying way of thinking about optimality criteria for fractional factorial split-plot designs, with or without blocking, and to construct catalogs of optimal designs; the second is to develop optimality criteria for semi-foldover plans for fractional factorial split-plot designs, with or without blocking, and to construct catalogs of optimal plans. With respect to analysis, there are also two broad objectives. The first objective is to use the post-data pivotal approach to provide an alternative way of analyzing data that arise from split-plot experiments in industry and to extend this approach to other types of industrial experiments. The post-data pivotal approach circumvents difficulties that occur with classical inference procedures in constrained parameter space problems. For example, these difficulties include negative estimates of variance components in split-plot experiments. The second objective is to develop new ways of analyzing data arising from computer experiments with functional output.
University of Manitoba - $14,000 Grant (2008-09) | Canada Spends