Beruflich Dokumente
Kultur Dokumente
Los Angeles, CA
(310) 476-7699
info@projectrisk.com
www.projectrisk.com
30d
Design Unit 1
0.07
Low=20d 0.06
PROBABILITY
Most 0.05
Likely=30 0.04
0.03
High=60d 0.02
0.01
0.00
20
24
28
32
36
40
44
48
52
56
© 2004 Hulett & Associates, LLC 5
Risk Along a Path
Most Likely
0.10CPM Date
Completion Date
PROBABILITY
0.08
0.06
0.04
0.02
0.00
11/15
11/24
12/12
12/21
12/30
12/3
1/8
1/17
1/26
2/4
© 2004 Hulett & Associates, LLC
Date
9
The Fallacy of Most Likely
Durations
• People sometimes say:
“Well, at least if we use the best estimates in our
schedule the CPM completion date is the most
likely date. Isn’t it?”
No, Never!
• In this case,
– CPM says December 4
– But the Most Likely completion date is
December 15
© 2004 Hulett & Associates, LLC 10
Cumulative Distribution
1.0
0.9
0.8
0.7 CPM
80% Likely
Value
0.6
0.5 Date
0.4 12/4 Schedule 1/3
0.3
0.2
0.1
0.0
11/15
11/24
12/12
12/21
12/30
12/3
1/8
1/17
1/26
2/4
Date
© 2004 Hulett & Associates, LLC 11
Results for Simple
Single-Path Schedule: CPM = 10%
Summary Statistics
for Project Finish
Minimum 11/18
Maximum 2/6
Mean 12/22
Std Deviation 13
Mode 12/15
5% 12/1
CPM
10% 12/5
20% 12/11
30% 12/14
40% 12/18
50% 12/21
60% 12/25
70% 12/29
80% 1/3 80%
©90%
2004 Hulett & Associates,
1/9 LLC 12
95% 1/14
Risk at Path Merge Points
The “Merge Bias”
Start
Finish
1.0
CPM Date
Prob of value <= X-Axis
0.9
0.8
0.7
0.6
Value
0.5
0.4
One-Path Two-Path
0.3 Schedule Schedule
0.2
0.1
0.0
11/15
11/22
11/29
12/13
12/20
12/27
11/1
11/8
12/6
1/3
1/10
1/17
1/24
1/31
2/7
Date
© 2004 Hulett & Associates, LLC 15
Comparison of Two Risky
Schedules: CPM < 5%
Evidence of the Merge Bias
Two Paths
One Path Merge Bias
Mean 12/22 12/29
Mode 12/18 12/31
Std Deviation 13.1 11.5
CPM
5% 12/1 12/11
CPM 10% 12/5 12/15
20% 12/11 12/19
30% 12/15 12/23
40% 12/18 12/26
50% 12/22 12/29
60% 12/25 1/1
70% 12/29 1/4
80% 1/2 1/8 80%
90%
© 2004 Hulett 1/9 1/13
& Associates, LLC 16
95% 1/14 1/19
Defining the
Risk Critical Path/Activities
• With hundreds or thousands of activities, which
are most likely to delay the project?
– Depends on risk, project structure (float)
• Simulation program records whether an activity
was critical in each iteration
Slack Path
Not Managed
Risk Managed
Critical Path
Correlation Matrix
Design / Build / Test /
Duration Duration Duration
Design/Duration 1 0.8 0.6
Build/Duration 0.8 1 0.9
Test/Duration 0.6 0.9 1
0.16
Not
Correlated
Relative Likelihood
0.12
Correlated
0.08
0.04
0.00
11/14
11/27
12/11
12/24
11/1
1/7
1/20
2/2
2/16
3/1
Date
© 2004 Hulett & Associates, LLC 23
Correlations Increase the
Spread of the Results
Distribution
S-Curve for Correlated and Not
Correlated Durations
Prob Value <= Value on
1.0 Not
0.9 Correlated
0.8
0.7 Correlated
X-Axis
0.6
0.5
0.4
0.3
0.2
0.1
0.0
11/14
11/27
12/11
12/24
11/1
1/7
1/20
2/2
2/16
3/1
Date
© 2004 Hulett & Associates, LLC 24
Probabilistic Branching
0.10 Branch
0.08
0.06
0.04
0.02
0.00
01
01
01
02
1
2
/0
/0
/0
/0
3/
2/
1/
7/
/5
19
25
16
/2
/1
/3
2/
11
1/
2/
3/
11
12
12
Date
© 2004 Hulett & Associates, LLC 28
Cumulative Distribution of
Probabilistic Branch
Cumulative Distribution for Finish
Prob of Value <= X-axis
1
0.8
Value
0.6
0.4 “Shoulder” at
70% Success
0.2
0
11 0 1
12 1
12 0 1
1/ 1
2/ 2
11 01
12 01
1/ 2
2
0
/0
/0
/0
0
0
6/
7/
0/
1/
3/
/
/
/5
/8
11
23
14
/1
/2
/2
/3
2/
11
Date
© 2004 Hulett & Associates, LLC 29
Conditional Branching
• Trade off
– Likelihood of completing on time
– Likelihood of using Preferred Technology A
1.0
0.9
0.8
0.7 Not
0.6 Leveled
0.5 Resource
0.4 Leveled
0.3
0.2
0.1
0.0
11/20
12/10
12/29
11/1
1/18
2/6
2/26
3/17
4/6
4/25
Date
1.0
0.9
0.8
0.7 Constrained
Value
0.6
0.5 Not
0.4
0.3 Constrained
0.2
0.1
0.0
11/13
11/25
12/19
12/31
11/1
12/7
1/12
1/24
2/5
2/17
Date
© 2004 Hulett & Associates, LLC 38
Advanced Project
Schedule Risk Analysis
Los Angeles, CA
(310) 476-7699
info@projectrisk.com
www.projectrisk.com