Ernest Forman - Academia.edu (original) (raw)

Papers by Ernest Forman

The Analytic Hierarchy Process—An Exposition

Operations Research, 2001

This exposition on the Analytic Hierarchy Process (AHP) has the following objectives: (1) to disc... more This exposition on the Analytic Hierarchy Process (AHP) has the following objectives: (1) to discuss why AHP is a general methodology for a wide variety of decision and other applications, (2) to present brief descriptions of successful applications of the AHP, and (3) to elaborate on academic discourses relevant to the efficacy and applicability of the AHP vis-a-vis competing methodologies. We discuss the three primary functions of the AHP: structuring complexity, measurement on a ratio scale, and synthesis, as well as the principles and axioms underlying these functions. Two detailed applications are presented in a linked document at http://mdm.gwu.edu/FormanGass.pdf .

The Analytic Hierarchy Process and Expert Choice

Decision by Objectives

AbstractThe following sections are included:The Analytic Hierarchy ProcessBeyond Weights and Scor... more AbstractThe following sections are included:The Analytic Hierarchy ProcessBeyond Weights and ScoresInconsistencyCauses of InconsistencyClerical ErrorLack of InformationLack of ConcentrationReal World Is Not Always ConsistentInadequate Model StructureCompensatory and Non-Compensatory Decision-makingPrinciples and Axioms of the Analytic Hierarchy ProcessExpert ChoiceDeveloping a Decision HierarchyGoalObjectivesAlternativesMore Complex HierarchiesEstablishing PrioritiesPairwise ComparisonsEigenvalues and EigenvectorsNumerical judgmentsGraphical judgmentsVerbal judgmentsSynthesisSensitivityA Typical Application of AHP/EXPERT CHOICEChoosing a Coast Guard Weapon Patrol Boat Fleet – BackgroundAlternativesObjectivesSub-objectivesReliability, Maintainability, and AvailabilityDerivation of preferences with respect to lowest level sub-objectivesPairwise verbal judgmentsVerbal judgments can be represented numericallyInconsistency RatioReducing InconsistencyPerformanceCOSTHUMAN FACTORSBASINGRESULTSensitivity AnalysisSeven Step Process for ChoiceOther decision-making ‘recipes’Musts and WantsSummary of the benefits of AHPIncremental ImprovementRetirement Places RatedBackgroundChange in methodology – from adding ranks to averaging scoresCreating ‘magic’ formulasDouble CountingEqual WeightingIncremental improvement using AHP

This paper illustrates how policy makers with different responsibilities can effectively particip... more This paper illustrates how policy makers with different responsibilities can effectively participate in a group decision involving coastal zone management policy. A group decision support system is used to help structure the discussion, provide meaningful measurements, synthesize over competing factors from different perspectives, and provide a record of the analysis for justifying and defending a policy if and when the rationale or process that led to the policy is questioned by those not involved in the deliberations.

Statistical models and methods for measuring software reliability

An analytic approach to marketing decisions

The need for decision support systems in marketing framework for decision making the evolution of... more The need for decision support systems in marketing framework for decision making the evolution of marketing decision support systems - review of major components of an MDSS MDSS for the choice phase - level three - decision analysis approaches an overview of the analytic hierarchy process underpinnnings of AHP and advanced AHP/EC applications situation analysis planning market strategy evaluation and control.

Decision support for the evaluation of the strategic defense initiative (Starwars)

Proceedings of the May 16-18, 1972, spring joint computer conference on - AFIPS '72 (Spring), 1971

Mathematical Modelling, 1987

The determination of priorities based on relative rather than absolute worth is sometimes questio... more The determination of priorities based on relative rather than absolute worth is sometimes questioned. This is surprising since it is commonly accepted that economic value is dependent on scarcity, and scarcity is by its very nature a relative property. This paper illustrates that when deriving priorities, relative worth is usually more appropriate than absolute worth, even though the results may sometimes seem counterintuitive. This paper also examines problems that can transpire if absolute rather than relative worth is used in situations where additional alternatives are subsequently introduced into an analysis.

The design for trustworthy software compilation the analytic hierarchy process (ahp) in software development

The Analytic Hierarchy Process (AHP) is an advanced technique that supports decision makers in st... more The Analytic Hierarchy Process (AHP) is an advanced technique that supports decision makers in structuring complex decisions, quantifying intangible factors, and evaluating choices in multiobjective decision situations. It is a comprehensive and rational decision-making framework that provides a powerful methodology for determining relative worth among a set of elements. AHP is especially suitable for complex decisions that involve the comparison of decision elements which are difficult to quantify. The AHP, and its more recent version the Analytic Network Process (ANP), were developed by Dr. Thomas Saaty and have been applied in a wide variety of decision situations in organizations worldwide. AHP is particularly applicable in managing software complexity, and in Quality Function Deployment (QFD), as presented in Chapter 11 of the book Design for Trustworthy Software.This short cut illustrates the application of AHP in prioritizing complex design issues. It also shows how AHP and its supporting software, Expert Choice (EC), can handle much higher levels of complexities accurately and expeditiously than the prioritization matrices introduced in Chapter 7 of Design for Trustworthy Software. In addition to solutions facilitated by EC, this short cut also illustrates two known approximations to AHP solutions using manual calculations. Manual calculations can be used to solve relatively less complex problems. They are presented in this short cut to illustrate the first principles and the steps involved in AHP.This short cut is a reproduction of Chapter 8 of the book Design for Trustworthy Software and introduces AHP with a simple example. It can be used either as a methodology in trustworthy software design process or as a standalone introductory presentation on AHP.This short cut should be of interest to software and quality professionals. In particular, it would be of value to the CMMI, Six Sigma, and DFSS communities worldwide, especially those who have acquired or plan to acquire Green Belt, Black Belt, Master Black Belt, or similar competencies in various quality management disciplines. It should also be a useful resource for students and academicians of various programs at senior undergraduate and graduate levels, and for those preparing for ASQ's Certified Software Quality Engineer (CSQE) examination.What This Short Cut Covers 3Introduction 4Prioritization, Complexity, and the Analytic Hierarchy Process 4Multiobjective Decision-Making and AHP 5Case Study 1 Solution Using Expert Choice 12Approximations to AHP with Manual Calculations 22Conclusion 33Key Points 33Additional Resources 34Internet Exercises 34Review Questions 34Discussion Questions and Projects 35Problems 36Endnotes 45What's in the Book Design for Trustworthy Software 47About the Authors 52The Design for Trustworthy Software Digital Short Cut Compilation 53

Method and apparatus for generating hierarchical displays

Method and apparatus are described for drawing tree structures on output displays and on printed ... more Method and apparatus are described for drawing tree structures on output displays and on printed output reports. The tree structures include complete illustration of nodes and branches connecting the same, and further provides display or printing of data associated with the various nodes. The central node of the tree may be arbitrarily selected by redrawing the structure to focus on the root node of the tree or on the arbitrarily selected central node. For economic use of display space, a skeletal display may be provided in which only the nodes descendent from the central node of interest are shown with the associated data, the remaining nodes being displayed in skeletal format only. The tree structure may be applied to a descision making algorithm, and may be used to provide a number of alternatives useful for attaining a desired goal, and for evaluating the various alternatives.

Mathematical Modelling, 1987

Value in Health, 2001

Decision-making is a process of assessing alternatives and their attributes versus an objective(s... more Decision-making is a process of assessing alternatives and their attributes versus an objective(s), trading-off various advantages and disadvantages, and ultimately synthesizing the information to culminate at a central point: a decision. The aim of the workshop is to outline a systematic process for group decision-making. A formulary decision incorporating clinical, economic and humanistic data from the perspective of a hospital committee will be used as an illustration. PARTICIPANTS WHO WOULD BENEFIT: Researchers who are involved in creating group decision-analytic models and systems, and stakeholders involved in formulary selection.

In search of the “right” model

Telematics and Informatics, 1986

Abstract When performing multiple regression we introduce and eliminate variables in an attempt t... more Abstract When performing multiple regression we introduce and eliminate variables in an attempt to find the “right” or underlying model. In a Box Jenkins time series analysis we use the data to help identify the “right” model and then fit the model to the data by estimating the model's parameters. This paper will address models for executive decision support and discuss how the use of understandable and flexible models makes it clear that there is no “right” model; that there are typically alternative models for alternative views and that the problem being solved will evolve during model development and refinement.

Guest editors' note

Telematics and Informatics, 1986

Promoting shared health care decision making using the analytic hierarchy process

Socio-Economic Planning Sciences, 1999

Recent developments in medical technology and bioethics have led to a shift in the traditional fr... more Recent developments in medical technology and bioethics have led to a shift in the traditional framework of physician–patient responsibility in health care decision making. Patients are increasingly participating in serious health care decisions, resulting in a “shared decision-making model“ that both patients and their doctors agree is a significant improvement over the traditional system in which a doctor served as

Mathematical and Computer Modelling, 1993

Despite the many books and jonmal articles that have appeared about the Analytic Hierarchy Proces... more Despite the many books and jonmal articles that have appeared about the Analytic Hierarchy Process (AHP), some important misconceptions about AHP remain. This paper discusses issues which underlie these misconceptions, including the cause and significance of "rank reversal," situations allowing or preventing rank reversals, the constraint of a 9 point scale, the roles of redundancy, intransitivities, and inconsistencies, the accommodation of objectivity and uncertainty, the similarities of AHP and Multi Attribute Utility Theory (MAUT), and opportunities to combine MCDM methodologies in real world decisions.

A Novel Computer Based Expert Decision Making Model for Prostate Cancer Disease Management

Journal of Urology, 2005

We propose a strategic, computer based, prostate cancer decision making model based on the analyt... more We propose a strategic, computer based, prostate cancer decision making model based on the analytic hierarchy process. We developed a model that improves physician-patient joint decision making and enhances the treatment selection process by making this critical decision rational and evidence based. Two groups (patient and physician-expert) completed a clinical study comparing an initial disease management choice with the highest ranked option generated by the computer model. Participants made pairwise comparisons to derive priorities for the objectives and subobjectives related to the disease management decision. The weighted comparisons were then applied to treatment options to yield prioritized rank lists that reflect the likelihood that a given alternative will achieve the participant treatment goal. Aggregate data were evaluated by inconsistency ratio analysis and sensitivity analysis, which assessed the influence of individual objectives and subobjectives on the final rank list of treatment options. Inconsistency ratios less than 0.05 were reliably generated, indicating that judgments made within the model were mathematically rational. The aggregate prioritized list of treatment options was tabulated for the patient and physician groups with similar outcomes for the 2 groups. Analysis of the major defining objectives in the treatment selection decision demonstrated the same rank order for the patient and physician groups with cure, survival and quality of life being more important than controlling cancer, preventing major complications of treatment, preventing blood transfusion complications and limiting treatment cost. Analysis of subobjectives, including quality of life and sexual dysfunction, produced similar priority rankings for the patient and physician groups. Concordance between initial treatment choice and the highest weighted model option differed between the groups with the patient group having 59% concordance and the physician group having only 42% concordance. This study successfully validated the usefulness of a computer based prostate cancer management decision making model to produce individualized, rational, clinically appropriate disease management decisions without physician bias.

Optimal Time Intervals for Testing Hypotheses on Computer Software Errors

IEEE Transactions on Reliability, 1979

This paper discusses certain stochastic aspects of the software reliability problem. First an emp... more This paper discusses certain stochastic aspects of the software reliability problem. First an empirical stopping rule for debugging and testing computer software is discussed. Then some results are presented on choosing a time interval for testing the hypothesis that a software system contains no errors, given certain cost and risk constraints.

Determining certainty factors with the analytic hierarchy process

Expert Systems with Applications, 1992

ABSTRACT Certainty factors are intended to measure the certainty of expert system rules. Since ce... more ABSTRACT Certainty factors are intended to measure the certainty of expert system rules. Since certainty factors represent a change in the probability of a hypothesis, given additional information about an event, a rule's certainty factor depends on the difference between posterior and prior probabilities. Developers of the MYCIN expert system (originators of the certainty factor concept) abandoned Bayes' Theorem and the p-function because they felt there were large areas of expert knowledge and intuition that, although amenable in theory to the frequency analysis of statistical probability, defied rigorous analysis, in part, because experts resisted expressing their reasoning process in coherent probabilistic terms. The Analytic Hierarchy Process (AHP) facilitates the practical acquisition of experts' knowledge and intuition in a way that produces ratio scale likelihoods with a theoretical basis that conforms to Bayes Theorem and the p-function. Although AHP is well known by decision analysts, it has not yet been widely applied to expert systems applications. We show how AHP can be used to develop prior and posterior probabilities and how these probabilities can be used to calculate certainty factors for expert system rules.

Aggregating individual judgments and priorities with the analytic hierarchy process

European Journal of Operational Research, 1998

The Analytic Hierarchy Process (AHP) is often used in group settings where group members either e... more The Analytic Hierarchy Process (AHP) is often used in group settings where group members either engage in discussion to achieve a consensus or express their own preferences. Individual judgments can be aggregated in different ways. Two of the methods that have been found ...

The Analytic Hierarchy Process—An Exposition

Operations Research, 2001

This exposition on the Analytic Hierarchy Process (AHP) has the following objectives: (1) to disc... more This exposition on the Analytic Hierarchy Process (AHP) has the following objectives: (1) to discuss why AHP is a general methodology for a wide variety of decision and other applications, (2) to present brief descriptions of successful applications of the AHP, and (3) to elaborate on academic discourses relevant to the efficacy and applicability of the AHP vis-a-vis competing methodologies. We discuss the three primary functions of the AHP: structuring complexity, measurement on a ratio scale, and synthesis, as well as the principles and axioms underlying these functions. Two detailed applications are presented in a linked document at http://mdm.gwu.edu/FormanGass.pdf .

The Analytic Hierarchy Process and Expert Choice

Decision by Objectives

AbstractThe following sections are included:The Analytic Hierarchy ProcessBeyond Weights and Scor... more AbstractThe following sections are included:The Analytic Hierarchy ProcessBeyond Weights and ScoresInconsistencyCauses of InconsistencyClerical ErrorLack of InformationLack of ConcentrationReal World Is Not Always ConsistentInadequate Model StructureCompensatory and Non-Compensatory Decision-makingPrinciples and Axioms of the Analytic Hierarchy ProcessExpert ChoiceDeveloping a Decision HierarchyGoalObjectivesAlternativesMore Complex HierarchiesEstablishing PrioritiesPairwise ComparisonsEigenvalues and EigenvectorsNumerical judgmentsGraphical judgmentsVerbal judgmentsSynthesisSensitivityA Typical Application of AHP/EXPERT CHOICEChoosing a Coast Guard Weapon Patrol Boat Fleet – BackgroundAlternativesObjectivesSub-objectivesReliability, Maintainability, and AvailabilityDerivation of preferences with respect to lowest level sub-objectivesPairwise verbal judgmentsVerbal judgments can be represented numericallyInconsistency RatioReducing InconsistencyPerformanceCOSTHUMAN FACTORSBASINGRESULTSensitivity AnalysisSeven Step Process for ChoiceOther decision-making ‘recipes’Musts and WantsSummary of the benefits of AHPIncremental ImprovementRetirement Places RatedBackgroundChange in methodology – from adding ranks to averaging scoresCreating ‘magic’ formulasDouble CountingEqual WeightingIncremental improvement using AHP

This paper illustrates how policy makers with different responsibilities can effectively particip... more This paper illustrates how policy makers with different responsibilities can effectively participate in a group decision involving coastal zone management policy. A group decision support system is used to help structure the discussion, provide meaningful measurements, synthesize over competing factors from different perspectives, and provide a record of the analysis for justifying and defending a policy if and when the rationale or process that led to the policy is questioned by those not involved in the deliberations.

Statistical models and methods for measuring software reliability

An analytic approach to marketing decisions

The need for decision support systems in marketing framework for decision making the evolution of... more The need for decision support systems in marketing framework for decision making the evolution of marketing decision support systems - review of major components of an MDSS MDSS for the choice phase - level three - decision analysis approaches an overview of the analytic hierarchy process underpinnnings of AHP and advanced AHP/EC applications situation analysis planning market strategy evaluation and control.

Decision support for the evaluation of the strategic defense initiative (Starwars)

Proceedings of the May 16-18, 1972, spring joint computer conference on - AFIPS '72 (Spring), 1971

Mathematical Modelling, 1987

The determination of priorities based on relative rather than absolute worth is sometimes questio... more The determination of priorities based on relative rather than absolute worth is sometimes questioned. This is surprising since it is commonly accepted that economic value is dependent on scarcity, and scarcity is by its very nature a relative property. This paper illustrates that when deriving priorities, relative worth is usually more appropriate than absolute worth, even though the results may sometimes seem counterintuitive. This paper also examines problems that can transpire if absolute rather than relative worth is used in situations where additional alternatives are subsequently introduced into an analysis.

The design for trustworthy software compilation the analytic hierarchy process (ahp) in software development

The Analytic Hierarchy Process (AHP) is an advanced technique that supports decision makers in st... more The Analytic Hierarchy Process (AHP) is an advanced technique that supports decision makers in structuring complex decisions, quantifying intangible factors, and evaluating choices in multiobjective decision situations. It is a comprehensive and rational decision-making framework that provides a powerful methodology for determining relative worth among a set of elements. AHP is especially suitable for complex decisions that involve the comparison of decision elements which are difficult to quantify. The AHP, and its more recent version the Analytic Network Process (ANP), were developed by Dr. Thomas Saaty and have been applied in a wide variety of decision situations in organizations worldwide. AHP is particularly applicable in managing software complexity, and in Quality Function Deployment (QFD), as presented in Chapter 11 of the book Design for Trustworthy Software.This short cut illustrates the application of AHP in prioritizing complex design issues. It also shows how AHP and its supporting software, Expert Choice (EC), can handle much higher levels of complexities accurately and expeditiously than the prioritization matrices introduced in Chapter 7 of Design for Trustworthy Software. In addition to solutions facilitated by EC, this short cut also illustrates two known approximations to AHP solutions using manual calculations. Manual calculations can be used to solve relatively less complex problems. They are presented in this short cut to illustrate the first principles and the steps involved in AHP.This short cut is a reproduction of Chapter 8 of the book Design for Trustworthy Software and introduces AHP with a simple example. It can be used either as a methodology in trustworthy software design process or as a standalone introductory presentation on AHP.This short cut should be of interest to software and quality professionals. In particular, it would be of value to the CMMI, Six Sigma, and DFSS communities worldwide, especially those who have acquired or plan to acquire Green Belt, Black Belt, Master Black Belt, or similar competencies in various quality management disciplines. It should also be a useful resource for students and academicians of various programs at senior undergraduate and graduate levels, and for those preparing for ASQ's Certified Software Quality Engineer (CSQE) examination.What This Short Cut Covers 3Introduction 4Prioritization, Complexity, and the Analytic Hierarchy Process 4Multiobjective Decision-Making and AHP 5Case Study 1 Solution Using Expert Choice 12Approximations to AHP with Manual Calculations 22Conclusion 33Key Points 33Additional Resources 34Internet Exercises 34Review Questions 34Discussion Questions and Projects 35Problems 36Endnotes 45What's in the Book Design for Trustworthy Software 47About the Authors 52The Design for Trustworthy Software Digital Short Cut Compilation 53

Method and apparatus for generating hierarchical displays

Method and apparatus are described for drawing tree structures on output displays and on printed ... more Method and apparatus are described for drawing tree structures on output displays and on printed output reports. The tree structures include complete illustration of nodes and branches connecting the same, and further provides display or printing of data associated with the various nodes. The central node of the tree may be arbitrarily selected by redrawing the structure to focus on the root node of the tree or on the arbitrarily selected central node. For economic use of display space, a skeletal display may be provided in which only the nodes descendent from the central node of interest are shown with the associated data, the remaining nodes being displayed in skeletal format only. The tree structure may be applied to a descision making algorithm, and may be used to provide a number of alternatives useful for attaining a desired goal, and for evaluating the various alternatives.

Mathematical Modelling, 1987

Value in Health, 2001

Decision-making is a process of assessing alternatives and their attributes versus an objective(s... more Decision-making is a process of assessing alternatives and their attributes versus an objective(s), trading-off various advantages and disadvantages, and ultimately synthesizing the information to culminate at a central point: a decision. The aim of the workshop is to outline a systematic process for group decision-making. A formulary decision incorporating clinical, economic and humanistic data from the perspective of a hospital committee will be used as an illustration. PARTICIPANTS WHO WOULD BENEFIT: Researchers who are involved in creating group decision-analytic models and systems, and stakeholders involved in formulary selection.

In search of the “right” model

Telematics and Informatics, 1986

Abstract When performing multiple regression we introduce and eliminate variables in an attempt t... more Abstract When performing multiple regression we introduce and eliminate variables in an attempt to find the “right” or underlying model. In a Box Jenkins time series analysis we use the data to help identify the “right” model and then fit the model to the data by estimating the model's parameters. This paper will address models for executive decision support and discuss how the use of understandable and flexible models makes it clear that there is no “right” model; that there are typically alternative models for alternative views and that the problem being solved will evolve during model development and refinement.

Guest editors' note

Telematics and Informatics, 1986

Promoting shared health care decision making using the analytic hierarchy process

Socio-Economic Planning Sciences, 1999

Recent developments in medical technology and bioethics have led to a shift in the traditional fr... more Recent developments in medical technology and bioethics have led to a shift in the traditional framework of physician–patient responsibility in health care decision making. Patients are increasingly participating in serious health care decisions, resulting in a “shared decision-making model“ that both patients and their doctors agree is a significant improvement over the traditional system in which a doctor served as

Mathematical and Computer Modelling, 1993

Despite the many books and jonmal articles that have appeared about the Analytic Hierarchy Proces... more Despite the many books and jonmal articles that have appeared about the Analytic Hierarchy Process (AHP), some important misconceptions about AHP remain. This paper discusses issues which underlie these misconceptions, including the cause and significance of "rank reversal," situations allowing or preventing rank reversals, the constraint of a 9 point scale, the roles of redundancy, intransitivities, and inconsistencies, the accommodation of objectivity and uncertainty, the similarities of AHP and Multi Attribute Utility Theory (MAUT), and opportunities to combine MCDM methodologies in real world decisions.

A Novel Computer Based Expert Decision Making Model for Prostate Cancer Disease Management

Journal of Urology, 2005

We propose a strategic, computer based, prostate cancer decision making model based on the analyt... more We propose a strategic, computer based, prostate cancer decision making model based on the analytic hierarchy process. We developed a model that improves physician-patient joint decision making and enhances the treatment selection process by making this critical decision rational and evidence based. Two groups (patient and physician-expert) completed a clinical study comparing an initial disease management choice with the highest ranked option generated by the computer model. Participants made pairwise comparisons to derive priorities for the objectives and subobjectives related to the disease management decision. The weighted comparisons were then applied to treatment options to yield prioritized rank lists that reflect the likelihood that a given alternative will achieve the participant treatment goal. Aggregate data were evaluated by inconsistency ratio analysis and sensitivity analysis, which assessed the influence of individual objectives and subobjectives on the final rank list of treatment options. Inconsistency ratios less than 0.05 were reliably generated, indicating that judgments made within the model were mathematically rational. The aggregate prioritized list of treatment options was tabulated for the patient and physician groups with similar outcomes for the 2 groups. Analysis of the major defining objectives in the treatment selection decision demonstrated the same rank order for the patient and physician groups with cure, survival and quality of life being more important than controlling cancer, preventing major complications of treatment, preventing blood transfusion complications and limiting treatment cost. Analysis of subobjectives, including quality of life and sexual dysfunction, produced similar priority rankings for the patient and physician groups. Concordance between initial treatment choice and the highest weighted model option differed between the groups with the patient group having 59% concordance and the physician group having only 42% concordance. This study successfully validated the usefulness of a computer based prostate cancer management decision making model to produce individualized, rational, clinically appropriate disease management decisions without physician bias.

Optimal Time Intervals for Testing Hypotheses on Computer Software Errors

IEEE Transactions on Reliability, 1979

This paper discusses certain stochastic aspects of the software reliability problem. First an emp... more This paper discusses certain stochastic aspects of the software reliability problem. First an empirical stopping rule for debugging and testing computer software is discussed. Then some results are presented on choosing a time interval for testing the hypothesis that a software system contains no errors, given certain cost and risk constraints.

Determining certainty factors with the analytic hierarchy process

Expert Systems with Applications, 1992

ABSTRACT Certainty factors are intended to measure the certainty of expert system rules. Since ce... more ABSTRACT Certainty factors are intended to measure the certainty of expert system rules. Since certainty factors represent a change in the probability of a hypothesis, given additional information about an event, a rule's certainty factor depends on the difference between posterior and prior probabilities. Developers of the MYCIN expert system (originators of the certainty factor concept) abandoned Bayes' Theorem and the p-function because they felt there were large areas of expert knowledge and intuition that, although amenable in theory to the frequency analysis of statistical probability, defied rigorous analysis, in part, because experts resisted expressing their reasoning process in coherent probabilistic terms. The Analytic Hierarchy Process (AHP) facilitates the practical acquisition of experts' knowledge and intuition in a way that produces ratio scale likelihoods with a theoretical basis that conforms to Bayes Theorem and the p-function. Although AHP is well known by decision analysts, it has not yet been widely applied to expert systems applications. We show how AHP can be used to develop prior and posterior probabilities and how these probabilities can be used to calculate certainty factors for expert system rules.

Aggregating individual judgments and priorities with the analytic hierarchy process

European Journal of Operational Research, 1998

The Analytic Hierarchy Process (AHP) is often used in group settings where group members either e... more The Analytic Hierarchy Process (AHP) is often used in group settings where group members either engage in discussion to achieve a consensus or express their own preferences. Individual judgments can be aggregated in different ways. Two of the methods that have been found ...