baxter - usingahp

Upload: ramirali

Post on 08-Apr-2018

238 views

Category:

Documents


0 download

TRANSCRIPT

  • 8/7/2019 Baxter - UsingAHP

    1/32

    Peter Baxter, DISTRIBUTIVE MANAGEMENT

    Hampton Roads INCOSE Decision Analysis Conference - Nov 2009

    USING ME A SURE ME NT A ND THE S AATY

    ME THOD TO CH O O S E T H E BEST

    DECISION ALTERNATIVE

  • 8/7/2019 Baxter - UsingAHP

    2/32

    OBJECTIVES

    Learn:

    How to construct and weight evaluationcriteria.

    How to make pair-wise comparisons ofalternatives.

    How to expand the example for morecomplex, nested types of criteria.

    How a measurement process can supportthe Saaty method.

    D I S T R I B U T I V E

    M A N A G E M E N T

    2

  • 8/7/2019 Baxter - UsingAHP

    3/32

    WHAT IS THE AHP/SAATYMETHOD?

  • 8/7/2019 Baxter - UsingAHP

    4/32

    SIMPLE DEFINITION

    Compute the matrix values for a and voila!

    The Analytic Hierarchy Process (AHP)

    D I S T R I B U T I V E

    M A N A G E M E N T

    4

  • 8/7/2019 Baxter - UsingAHP

    5/32

    COMPARE THE SIZES

    OF THESEC

    IRCLES

    A B C D E

    A B C D E

    A 1 7 9 5 3

    B 1/7 1 3 1/5 1/7

    C 1/9 1/3 1 1/7 1/9

    D 1/5 5 7 1 1/3

    E 1/3 7 9 3 1D I S T R I B U T I V E

    M A N A G E M E N T

    5

  • 8/7/2019 Baxter - UsingAHP

    6/32

    SCALE OF COMPARISON

    Dont need an absolute scale

    (if you already know the size of all but one)

    Relative scale approximates difference

    D I S T R I B U T I V E

    M A N A G E M E N T

    6

  • 8/7/2019 Baxter - UsingAHP

    7/32

    SIMPLE EXPERIMENT

    One test is worth 1000 expert opinionsD I S T R I B U T I V E

    M A N A G E M E N T

    7

  • 8/7/2019 Baxter - UsingAHP

    8/32

    WEBERS EXPERIMENT

    In 1846 Weber found, for example, that people while holding in

    their hand different weights, could distinguish between a

    weight of 20 g and a weight of 21 g, but could not if the

    second weight is only 20.5 g.On the other hand, while they

    could not distinguish between 40 g and 41 g, they could

    between 40 g and 42 g, and so on at higher levels. We need

    to increase a stimulus s by a minimum amount s to reach a

    pointwhere our senses can first discriminate between s and

    s+s. s is called the just noticeable difference (jnd). The

    ratio r = s/s does not depend on s.

    Webers law states that change in sensation is noticed when the stimulus

    is increased by a constant percentage of the stimulus itself. This law

    holds in ranges where s is small when compared with s, and hence

    in practice it fails to hold when s is either too small or too large.D I S T R I B U T I V E

    M A N A G E M E N T

    8

  • 8/7/2019 Baxter - UsingAHP

    9/32

    WHY IT WORKS

    People are inconsistent at providing an absolutescale to evaluate objects.

    How much does Rock A weigh?

    How much does Rock B weigh?

    There are better at comparing pairs of objects.

    Does Rock A weigh more than Rock B?

    D I S T R I B U T I V E

    M A N A G E M E N T

    9

  • 8/7/2019 Baxter - UsingAHP

    10/32

    APPLYING THE TECHNIQUE

    1. Select criteria(s) to evaluate

    2. Define comparison scale

    3. Perform pair-wise comparison

    4. Check consistency

    5. Calculate values

    D I S T R I B U T I V E

    M A N A G E M E N T

    10

  • 8/7/2019 Baxter - UsingAHP

    11/32

    APPLYING THE METHOD

  • 8/7/2019 Baxter - UsingAHP

    12/32

    EXAMPLE #1

    SOFTWARE ESTIMATION

    A controlled test where existing software sizes are known.

    Ask 30 grad students to estimate the SLOC of common data

    structures like stack, queue, list.

    Estimate SLOC three ways:

    1. Guess a number.

    2. Compare to one reference structure using numeric

    scale.

    3. Compare to one reference structure using relative scale.

    Plot results

    From Establishing Software Size Using Pair-wise Comparison Method

    by Eduardo Miranda

    D I S T R I B U T I V E

    M A N A G E M E N T

    12

  • 8/7/2019 Baxter - UsingAHP

    13/32

    EXAMPLE #1

    SOFTWARE ESTIMATION

    D I S T R I B U T I V E

    M A N A G E M E N T

    13

  • 8/7/2019 Baxter - UsingAHP

    14/32

    EXAMPLE #1

    OBSERVATIONS

    Mirandas Observations

    The high variability of the finger in the wind approach,

    which is almost two to three times bigger than the

    corresponding paired comparisons method.

    The high correlation, r = .979, existing between the

    relative sizes of modules independent of the estimation

    method employed. This seems to corroborate the

    premise that the human mind is better at establishingdifferences than at guessing absolute values.

    D I S T R I B U T I V E

    M A N A G E M E N T

    14

  • 8/7/2019 Baxter - UsingAHP

    15/32

    EXAMPLE #2

    SYSTEM REQUIREMENTS

    From an SEI study Requirements Prioritization Case Study

    Using AHP by Nancy Mead.

    Given nine security requirements, decide which one(s) have

    greatest cost-benefit.

    Benefits

    By using AHP, the requirements engineer can

    also confirm the consistency of the result. AHP can

    prevent subjective judgment errors and increase the

    likelihood that the results are reliable.

    D I S T R I B U T I V E

    M A N A G E M E N T

    15

  • 8/7/2019 Baxter - UsingAHP

    16/32

    EXAMPLE #2

    APPROACH

    Approach

    1. Review requirements for completeness.

    2. Apply pair-wise comparison for value.

    3. Apply pair-wise comparison for implementationcost.

    4. Calculate AHP matrix and diagram for value & cost.

    5. Use resulting diagram for analyzing requirements.

    D I S T R I B U T I V E

    M A N A G E M E N T

    16

  • 8/7/2019 Baxter - UsingAHP

    17/32

    EXAMPLE #2

    COMPARISON SCALE

    D I S T R I B U T I V E

    M A N A G E M E N T

    17

  • 8/7/2019 Baxter - UsingAHP

    18/32

    EXAMPLE #2

    COMPARISON

    Compare one attribute of each requirement to another

    requirement using a relative scale.

    #1 is same

    as #1

    #1 is greater

    than #2

    #2 is much

    less than #8

    D I S T R I B U T I V E

    M A N A G E M E N T

    18

  • 8/7/2019 Baxter - UsingAHP

    19/32

    ABOUT CONSISTENCY

    If: A > B > C

    Then: C > A is wrong

    AHP contains a technique to calculate the extent ofpair-wise consistency, which can then be

    compared to a consistency tolerance.

    AHP can also indicate which pair-wise comparison(like the one above) is inconsistent.

    D I S T R I B U T I V E

    M A N A G E M E N T

    19

  • 8/7/2019 Baxter - UsingAHP

    20/32

    EXAMPLE #2

    COMPARISON SUMMARY

    D I S T R I B U T I V E

    M A N A G E M E N T

    20

  • 8/7/2019 Baxter - UsingAHP

    21/32

    EXAMPLE #2

    FINDINGS

    Client feedback

    It may be beneficial to see the consistency matrix.

    Understand weight of cost and value.

    Difficult to understand the motivation of each

    reviewer.

    D I S T R I B U T I V E

    M A N A G E M E N T

    21

  • 8/7/2019 Baxter - UsingAHP

    22/32

    OTHER EXAMPLES

    From Saaty:

    Evaluate the best city in China for Disney

    to build a new theme park.

    Determine optimum foreign relationspolicy for dealing with Iran.

    Estimate market share of super retail

    stores.

    Selecting a school.

    D I S T R I B U T I V E

    M A N A G E M E N T

    22

  • 8/7/2019 Baxter - UsingAHP

    23/32

    MEASUREMENT AND AHP

  • 8/7/2019 Baxter - UsingAHP

    24/32

    MEASUREMENT AND AHP

    Goal is for Measurement to support AHP estimation

    Estimate

    Plan

    Monitor& Control

    Capitalize

    Measurement Process

    Use AHP

    D I S T R I B U T I V E

    M A N A G E M E N T

    24

  • 8/7/2019 Baxter - UsingAHP

    25/32

    TYPICAL MEASUREMENT

    PROCESS

    Evaluate

    Establish

    Capability

    Technical

    and Management

    ProcessesINFORMATION

    NEEDS

    ANALYSIS RESULTS

    ANALYSIS

    RESULTSAND

    PERFORMANCE

    MEASURESIMPROVEMENT

    ACTIONS

    Measurement Process

    USER FEEDBACK

    Plan Perform

    Core Measurement Process

    Experience

    Base

    MEAS-

    UREMENT

    PLAN

    25

  • 8/7/2019 Baxter - UsingAHP

    26/32

    WHAT TO MEASURE?

    Measurement Requirements = information needs

    Based on your business needs.(not a pre-defined list)

    Information needs are:

    Input to the measurement process.

    Provided by the management and technical process thatneed information to perform their jobs.

    Become the requirements for measurement process.

    Refined into measures and then resulting informationproducts are provided to the users.

    D I S T R I B U T I V E

    M A N A G E M E N T

    26

  • 8/7/2019 Baxter - UsingAHP

    27/32

    COMMON PROJECT

    MEASURES

    Cost

    Staffing , Staff Hours

    Functional / Requirements Size

    SLOC

    Defects

    Estimation Project/Program Store

    Factors estimate

    using HP

    D I S T R I B U T I V E

    M A N A G E M E N T

    27

    Usually there is opportunity for measurement to support AHP since

    there is overlap between what is estimated and what is measured

  • 8/7/2019 Baxter - UsingAHP

    28/32

    MEASUREMENT GUIDE AHP

    Measurement contains project attributes:

    Lifecycle model

    Principle architecture

    Application domain

    AHP estimation of projects with similar attributes.

    Reference sizes should not differ by more than an

    order of magnitude.

    D I S T R I B U T I V E

    M A N A G E M E N T

    28

  • 8/7/2019 Baxter - UsingAHP

    29/32

    AHPIN USE

    Estimate total staff hours in person years using data from

    five completed projects sharing similar attributes.

    D I S T R I B U T I V E

    M A N A G E M E N T

    29

  • 8/7/2019 Baxter - UsingAHP

    30/32

    RESOURCES

    Requirements Prioritization Case Study Using AHP

    by Nancy Mead Software Engineering Institute

    Establishing Software Size Using the Paired

    Comparisons Method by Eduardo Miranda

    Relative Measurement and Its Generalization in

    Decision Making Why Pairwise Comparisons are

    Central in Mathematics for the Measurement of

    Intangible Factors The Analytic

    Hierarchy/Network Process by Thomas Saaty

    D I S T R I B U T I V E

    M A N A G E M E N T

    30

  • 8/7/2019 Baxter - UsingAHP

    31/32

    QUESTIONS

    D I S T R I B U T I V E

    M A N A G E M E N T

    31

  • 8/7/2019 Baxter - UsingAHP

    32/32

    Peter Baxter

    Distributive Management

    www.distributive.com

    [email protected]

    D I S T R I B U T I V E

    M A N A G E M E N T

    32