This 3-day course is de¬signed for the professional program manager, system engineer, or project manager engaged in technically challenging projects where close technical collaboration between engineering and management is a must. To that end, this course addresses major topics that bridge the disciplines of project management and system engineering. Each of the selected topics is presented from the perspective of quantitative methods. Students first learn a theory or narrative, and then related methods or practices. Ideas are demonstrated that are immediately applicable to programs and projects. Attendees receive a copy of the instructor’s text, Quantitative Methods in Project Management.
Human Factors of XR: Using Human Factors to Design XR Systems
ATI's Quantitative Methods course: Bridging Project Management and System Engineering Technical Training Short Course
1. Video Sampler From ATI Professional Development Short Course
Quantitative Methods: Bridging Project Management and System Engineering
Instructor:
John C. Goodpasture, PMP
ATI Course Schedule: http://www.ATIcourses.com/schedule.htm
ATI's Quantitative Methods: http://www.aticourses.com/Quantitative_Methods.htm
2. www.ATIcourses.com
Boost Your Skills 349 Berkshire Drive
Riva, Maryland 21140
with On-Site Courses Telephone 1-888-501-2100 / (410) 965-8805
Tailored to Your Needs
Fax (410) 956-5785
Email: ATI@ATIcourses.com
The Applied Technology Institute specializes in training programs for technical professionals. Our courses keep you
current in the state-of-the-art technology that is essential to keep your company on the cutting edge in today’s highly
competitive marketplace. Since 1984, ATI has earned the trust of training departments nationwide, and has presented
on-site training at the major Navy, Air Force and NASA centers, and for a large number of contractors. Our training
increases effectiveness and productivity. Learn from the proven best.
For a Free On-Site Quote Visit Us At: http://www.ATIcourses.com/free_onsite_quote.asp
For Our Current Public Course Schedule Go To: http://www.ATIcourses.com/schedule.htm
3. Why number ideas are important for project management
Cardinal Ordinal Deterministic Random
• Metric • Rank choice • Numerical • Risk analysis
calculation & priority reporting to • Calculations
• Metric • Rank stakeholders and estimates
reporting complexity • Population of random or
• Budgets, sche • Give statistics probabilistic
dules, resourc numerical quantities
es visualization
to position
and rank
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved 2
4. Example: developer ranking of complexity
Histogram of developer opinion
Count [cardinal]
8 15
76th
30 Percentile
20
4 30 76% of rankings
15
are 4 or a 2
2 4 8
2 20
Rank [ordinal]
• Minimum 2
• Maximum 8
• Median 5
3
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved
5. Comparison of deterministic and random numbers
• Deterministic
– Single point, one value
– Certain knowledge
2
– Arithmetic on number values
• Probabilistic, aka random
– Range of possible values, with probabilities
– Different values occur from one trial or instance to the next
– Arithmetic on {value, value probability} pairs
– Most useful for project management if distribution is stationary
[invariant] with time and position
2.1
1 1.5
2 2.5
4
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved 4
6. Arithmetic operations with random numbers
• Arithmetic operations require operations on distribution functions
– Functional operations are often quite complex
– Simulation methods substitute for direct calculations
• As a practical matter, distributions are not often known
– Only observations of distribution outcomes are known
– Arithmetic operations applied to outcomes
– Approximations are made using simpler functions as substitutes
– Simulation methods derive estimators for actual—but unknown—
functions
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved 5
7. Logical operations with random numbers
• UNION and INTERSECTION
– Logical representation of addition and multiplication
• Logic operations provide practical and useful approximations of
outcomes
Union or Summation
A or B
A+ B
Intersection or Multiplication
A and B
A* B
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved 6
8. The Project Balance Sheet Tool
Quantitative Methods in Project Management
7
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved
9. Recall the “Project Balance Sheet”
Project Value from Project Estimate from
the Top Down the Bottom Up
Risk
Investor Value
Expectation &
Resource
Commitment Deliverables
Cost
Schedule
Management investment Project employment
of investment
8
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved
10. Map from business to project
1. Disaggregate sponsor needs: break down expectations, judgments, and
commitments into component parts
2. Categorize component parts into capacity, capability, resource needs, and risk
2. Re-integrate component parts to identify gaps and missing parts
Resource
Sponsor Capacity Capability Risk
Needs
Expectations Resources, sk Schedule
ills, commitm Feature X
ent
All the
Value features and
Cost
judgments functions of
widget A
Environment, Dollars and
Resource tools People, proce schedule
Commitment ss, tools
9
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved
11. Plot confidence in cost [or schedule]
Confidence that the
$_amount will not be
exceeded
Likely Risk
Very High
High
Medium
Low
Not to exceed cost $450K $475K $550K >$550K
10
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved
12. Plot timeline of project expense and business value
Business value
Project Business value
expenses from sales
$450K
$550K
11
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved
13. Sampling Metrics for Project Estimates
Quantitative Methods in Project Management
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved 12
14. In the beginning, there is a population
• All the data values, events, or event
Population outcomes that share a common situation or
environment
• Space that holds all the values of the
Population space population
• May be deterministic or the outcome of a
Population values random process in/of the population
• Only those populations that bear upon
Population project results are important
importance • Because a population bears upon project
results, the population is important
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved 13
15. Sampling risks
Accuracy Completeness
• Misunderstood • Excluded clusters or strata
exclusions, clusters, or strata • Unrepresentative data quality
• Unrepresentative sample data or deficiency
value outliers
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved 14
16. Two risk assessments to be made
Margin of error Confidence interval
Estimated error around the
Interval that probably contains the
measurement, observation, or
true population parameter
calculation of statistics
Confidence expresses probability
Interval of possible values for the
that the true parameter is in the
statistic relative to the statistic
interval
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved 15
17. Margin of error example
Margin of error % = 3 / 18 (x100) = 16.7%
18 Statistic
17 Sample Interval of statistic values: 3 20
½ Interval Margin of error % = +/- 1.5 / 18 (x100) = +/- 8.3%
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved 16
18. Confidence interval
• For some probability—for example, 95%--the true population
statistic is within the interval
– 5% of the trials may not have intervals that contain the true population
– For a single trial, there is a 95% confidence that the true population
statistic is within the sample interval
For 95/100 trials
Sample interval contains the true population statistics
For 1 trial
5% chance the interval does not contain the true population statistics
18 Statistic
Sample Interval of statistic: 3
17 20
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved 17
19. Confidence interval for proportional data
Interval = p +/- Z * [p * (1 - p) / N]
Where
Z is range value of standard Normal distribution
Z is normalized to the standard deviation
Z = 1 means 1 σ from the mean
Z range
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved 18
20. Margin of error, proportional data
+/- Margin of Error = ½ Interval width / p
Where ½ Interval width = +/- Z * [p * (1 - p) / N]
Z = 1.96
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved 19
21. Hypothesis Testing
Quantitative Methods in Project Management
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved 20
22. What if …. ?
Design parameter change
– You change a system design parameter with an expectation that there
will be a difference in performance.
– Comparing the ‘before’ to the ‘after’, is the difference a matter of
chance, or has there been a systemic change in performance?
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved 21
23. Distributions of X and Y
Sample X
Sample Y
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved 22
24. • We don’t know the distributions of sample X and sample Y (usually)
– Not needed for hypothesis test
– Distributions of sample average are known approximately
Sample average distribution
Sample X
Sample Y
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved 23
25. • H0 likely TRUE for difference values < 0.219
• Otherwise, likely FALSE
• With confidence of 95%
H0 distribution & confidence curve
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved 24
26. Risk mitigation in time and resource schedules
Quantitative Methods in Project Management
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved 25
27. Any issues?
Should you be equally confident of making the milestone?
Tandem path primitive
Parallel path primitive
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved 26
28. Interpreting the Confidence “S” Curve
A. 68% confidence: value between -1 to +1
B. 16% confidence: value > 1
C. 84% confidence: value < 1
B
1
0.84
0.75
0.5 A
0.25
0.16
C
0
-3.5 -3 -2.5 -2 -1.5 -1 -0.5 0 0.5 1 1.5 2 2.5 3 3.5
C A B
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved 27
29. Schedule example for tandem tasks
Schedule network primitive Task duration distribution, D
Task Probability distribution
0.45
0.4
Task A Task B 0.35
0.3
0.25
0.2
0.15
0.1
0.05
0
1 2 3 4 5 6
Duration range 1 - 6
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved 28
31. Confidence for “schedule-at-mode”
Date 1/1 1/21
2/12
3/15
3/25
1.2 Low confidence in 3/25
1
p/v
0.8
Calculate Confidence 0.6
0.4
0.2
0.0 0.5 0
1-Apr
2-Apr
4-Apr
23-Mar
24-Mar
25-Mar
26-Mar
27-Mar
28-Mar
29-Mar
30-Mar
3-Apr
5-Apr
31-Mar
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved 30
32. Parallel path primitive
What is the schedule
confidence at the milestone?
Distribution of tasks
0.45
0.4
0.35
0.3
0.25
0.2
Confidence: 80% at 4
1.2
0.15
0.1 1
0.05 0.8
0
1 2 3 4 5 6 0.6
0.4
0.2
0
1 2 3 4 5 6
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved 31
33. “Critical Chain” buffers uncertainty
1 2
10 days 11 days 12 days Buffer Project Buffer
Path buffer mitigates
15 days 10 days
“shift right” at the
milestone of joining
path
Task on the critical path
Task with risky duration, not on critical path
Critical chain is a concept developed in the book
Critical Chain (Goldratt, 1997)
Copyright 2011 Square Peg Consulting, LLC, All Rights Reserved 32
34. To learn more please attend ATI course
Quantitative Methods: Bridging Project Management and System Engineering
Please post your comments and questions to our blog:
http://www.aticourses.com/blog/
Sign-up for ATI's monthly Course Schedule Updates :
http://www.aticourses.com/email_signup_page.html