Figures

1.1 Principal Flow of Prior Topic Knowledge Between Volumes
2.1 Norden-Rayleigh Curve Compared with Standard Rayleigh Probability Distribution
2.2 Norden-Rayleigh Curve as a Truncated Cumulative Rayleigh Probability Distribution
2.3 Implication of a Norden-Rayleigh Curve as a Truncated Rayleigh Probability Density Function
2.4 Indicative Example of F/A-18 EMD Costs Plotted Against a Rayleigh Distribution
2.5 Indicative Example of F/A-22 EMD Costs Plotted Against a Rayleigh Distribution
2.6 Phased Semi-Independent Developments with an Elongated Single Hump
2.7 Phased Semi-Independent Developments with Suppressed Double Hump
2.8 The Penalty for Underestimating the Complexity of Solution Development
2.9 The Penalty of Late Resourcing
2.10 The Opportunity of Late Resourcing
2.11 Optimistic View of Premature Resource Reduction
2.12 More Pragmatic View of Premature Resource Reduction Using the Marching Army Principle
2.13 Marching Army Penalties for Premature Resource Reduction at Different Intervention Points
2.14 The Anomalous Distribution of the Marching Army Cost Penalties
2.15 Premature Resource Reduction Using a Disaggregation (Bactrian Camel) Technique
2.16 Premature Resource Reduction at the Mode Using the Disaggregation Technique
2.17 Premature Resource Reduction Using the Modal Re-Positioning Technique
2.18 Probability Density Function for a Beta Distribution
2.19 How Good is the Best Fit Beta Distribution for a Truncated Norden-Rayleigh Curve?
2.20 Solver Results for the Best: Fit Beta Distribution for a Range of NRC Truncation Ratios
2.21 Best Fit PERT-Beta Distribution tor a NRC Truncation Ratio of 3.5
2.22 PERT-Beta Distribution PDF cf. Norden-Rayleigh Resource Profile
2.23 Best Fit Triangular Distribution PDF cf. Norden-Rayleigh Resource Profile
2.24 Best Fit Triangular Distribution CDF cf. Norden-Rayleigh Spend Profile
2.25 Best Fit Weibull Distribution for the Sum of Two Norden-Rayleigh Curves (1)
2.26 Best Fit Weibull Distribution for the Sum of Two Norden-Rayleigh Curves (2)
2.27 Best Fit Beta Distribution for the Sum of Two Norden-Rayleigh Curves (1)
2.28 Best Fit Beta Distribution for the Sum of Two Norden-Rayleigh Curves (2)
2.29 Extrapolating NRC to Completion Using the Guess and Iterate Technique (1)
2.30 Extrapolating NRC to Completion Using the Guess and Iterate Technique (2)
2.31 Extrapolating NRC to Completion Using the Guess and Iterate Technique (3)
2.32 Extrapolating a PERT-Beta Lookalike to Completion Using a Guess and Iterate Technique (1)
2.33 Extrapolating a PERT-Beta Lookalike to Completion Using a Guess and Iterate Technique (2)
2.34 Extrapolating a NRC to Completion Using Microsoft Excel's Solver (1)
2.35 Extrapolating a NRC to Completion Using Microsoft Excel's Solver (2)
2.36 Extrapolating a PERT-Beta Lookalike to Completion Using Microsoft Excel's Solver (1)
2.37 Extrapolating a PERT-Beta Lookalike to Completion Using Microsoft Excel's Solver (2)
2.38 Solver Model Results for Linear Transformation of a Norden-Rayleigh Curve (1)
2.39 Solver Model Results for Linear Transformation of a Norden-Rayleigh Curve (2)
2.40 Solver Outturn Creep Follows the Average of the Two Schedule Slippage Cost Rules
2.41 Solver Outturn Creep Trend Analysis
2.42 Transformation of a ‘Perfect’ Norden-Rayleigh Curve to a Linear Form
2.43 Distortion of the Linear Transformation of a NRC due to Negative Log Values
2.44 Extrapolating a NRC to Completion Using a Transformation and Regression Technique (1)
2.45 Extrapolating a NRC to Completion Using a Transformation and Regression Technique (2)
2.46 Solver Outturn Creep Trend Analysis
2.47 Creating a 3-Point Estimate at Completion Using Alternative Techniques
3.1 Probability Distribution for the Sum of the Values of Two Dice
3.2 Sum of the Values of Two Dice Based on 36 Random Rolls (Twice)
3.3 Sum of the Values of Two Dice Based on 108 and 1,080 Random Rolls
3.4 Sum of the Values of Two Dice Based on 10,800 Random Rolls
3.5 Cumulative Frequency of the Sum of Two Dice Being less than or Equal to the Value Shown
3.6 Cumulative Distribution of the Sum of the Values of Five Dice Based on 10,000 Random Rolls
3.7 Probability Mass Function lor a 5 Dice Score cf. Normal Distribution
3.8 Height Distribution of Randomly Selected School Children Aged 5-11
3.9 Age Distribution of Randomly Selected School Children Aged 5-11
3.10 Percentile Height School Children Ages 5-11
3.11 Height Distribution of Randomly Selected School Children Aged 5-11
3.12 Height Distribution of Randomly Selected Schoolgirls Aged 5-18
3.13 Percentile Growth Charts for UK Girls Aged 5-18
3.14 Height Distribution of Randomly Selected Schoolgirls Aged 5-18
3.15 Height Distribution of Randomly Selected Schoolboys Aged 5-18
3.16 Percentile Growth Charts for UK Boys Aged 5-18
3.17 Height Distribution of Randomly Selected Schoolboys Aged 5-18
3.18 Height Distribution of Randomly Selected Schoolchildren Aged 5-18
3.19 Sample Monte Carlo Simulation PDF Output Based on 10,000 Iterations
3.20 Sample Monte Carlo Simulation CDF Output Based on 10,000 Iterations
3.21 Comparison of Two Monte Carlo Simulations of the Same Cost Model
3.22 Approximation of 5 Beta Distributions by 5 Triangular Distributions
3.23 Comparison of Two Monte Carlo Simulations with Appropriate Substituted Distributions
3.24 Comparison of Two Monte Carlo Simulations with Inappropriate Substituted Distributions (1)
3.25 Comparison of Two Monte Carlo Simulations with Inappropriate Substituted Distributions (2)
3.26 Making an Appropriate Informed Choice of Distribution for Monte Carlo Simulation (1)
3.27 Making an Appropriate Informed Choice of Distribution for Monte Carlo Simulation (2)
3.28 Three Example Beta Distributions with Common Start, Mode and Finish Points
3.29 Monte Carlo Simulation–Comparison Between Independent and 100% Correlated Tasks
3.30 Enforcing a 100% Rank Correlation Between Two Beta Distributions
3.31 Conceptual Models for Correlating Multiple Variables
3.32 Example of 50% Chain-Linked Correlation Using a Normal Copula
3.33 Chain-Linked Output Correlation for Cost Items 1 and 2
3.34 Impact of Chain-Linked Correlation on ‘Controlled’ Variable Value
3.35 Impact of Chain-Linked Correlation on Sum of Variable Values
3.36 Generation of a Chain-Linked Correlation Matrix
3.37 Example of 50% Chain-Linked Correlation Where the Chain Sequence has been Reversed
3.38 Example of 50% Hub-Linked Correlation
3.39 Consequential Hub-Linked Correlation for Cost Items 2 and 3
3.40 Example of 50% Hub-Linked Correlation Using a Different Hub Variable
3.41 Using Hub-Linked Correlation with a Dummy Variable to Derive Isometric Correlation
3.42 Using Hub-Linked Correlation with a Dummy Variable to Derive 25% Isometric Correlation
3.43 25% Isometric Correlation Across Baseline Activities Plus One 50% High Impact Risk
3.44 25% Isometric Correlation Across Baseline Activities Plus One 25% High Impact Risk
3.45 25% Isometric Correlation Across Baseline Activities Plus Two 50% High Impact Risks
3.46 25% Isometric Correlation Across Baseline Activities with Four Risks and One Opportunity
3.47 Monte Carlo Output for Four Independent Risks and One Opportunity (not Baseline Tasks)
3.48 Monte Carlo Output Post Mitigation of Risk 1
3.49 Monte Carlo Simulation of Number of Risks Likely to Occur
3.50 Swapping an Uncertainty Range with an Opportunity and a Risk Around a Fixed Value
3.51 Extreme Risks are Difficult to Spot and Easily Overlooked
3.52 Extreme Risks are Easier to Spot in the Context of Risks and Opportunities Only
3.53 Impact of Extreme Risks on Cost Model Confidence Levels
3.54 Impact of Modelling Probabilities of Occurrence with Uncertainty Distributions (1)
3.55 Impact of Modelling Probabilities of Occurrence with Uncertainty Distributions (2)
3.56 3×3 Latin Square Sampling Combinations for Three Confidence Intervals
3.57 Example of Bootstrap Sampling with a Small Empirical Distribution
3.58 Layering Delphi Technique Expert Range Estimates
4.1 Example of Marching Army Technique
4.2 Example of Historical Exchange Rate Data
4.3 Choosing a Bottom-Up Estimate Using Monte Carlo Simulation Output
4.4 Slipping and Sliding Technique
4.5 Slipping and Sliding Technique with Large Stretch Factor
4.6 Slipping and Sliding Technique with Very Pessimistic Schedule Assumption
4.7 Slipping and Sliding Technique with a Nonsensical Stretch Factor of Less than One
5.1 Example Monte Carlo Simulation with Four Independent Risks and One Opportunity (Excluding the Baseline Costs) - Range and Likelihood of Potential Cost Outcomes
6.1 Critical Path for an Example Estimating Process
6.2 Resource Profiling (Unsmoothed) Using Earliest Start and Finish Dates Around Critical Path
6.3 Resource Profile Smoothing Using Activity Float Around the Critical Path
6.4 Critical Path Accelerated by Removing Activities
6.5 Critical Path Uncertainty
7.1 Simple Queueing System
7.2 Single Queue, Single Channel System
7.3 Single Queue, Multiple Channel System
7.4 Multiple Queue, Multiple Channel System (with Queue Hoppers!)
7.5 Multiple Queue, Single Channel System (with Queue Hoppers!)
7.6 Difference Between Distribution of Arrivals and the Inter-Arrival Time Distribution
7.7 Equivalence of Poisson and Exponential Distributions
7.8 The Curse and Cause of Phantom Bottlenecks on Motorways
7.9 Example of a Single Channel Repair Facility with an Unbounded Repair Time Distribution
7.10 Example Queue Lengths for a Single Channel Repair Facility with Unbounded Repair Times
7.11 Example of a Single Channel Repair Facility with a Bounded Repair Time Distribution
7.12 Example Queue Lengths for a Single Channel Repair Facility with Bounded Repair Times
7.13 Example of a 3-Channel Repair Facility with an Unbounded Repair Time Distribution
7.14 Example of a 4-Channel Repair Facility with an Unbounded Repair Time Distribution
7.15 Example of a 3-Channel Repair Facility with a Bounded Repair Time Distribution
7.16 Apparent Reducing Demand for Repairs Over 12 Months
7.17 Apparent Reducing Demand for Repairs Over 24 Months
7.18 Constant Demand for Repairs Over 48 Months
7.19 Comparing the Observed Repair Arisings per Month with a Poisson Distribution
7.20 Weibull Distribution with Different Shape Parameter Values
7.21 A Bath Tub Curve Generated by an Exponentiated Weibull Distribution
7.22 Example of Time-Adjusted G/M/l Queueing Model
..................Content has been hidden....................

You can't read the all page of ebook, please click here login for view all page.
Reset
18.119.235.79