Anomaly detection and data imputation within time series
Chapter 5 slides
1. REASONS FOR VARIATION IN ACTIVITY
DURATION
1. Varying skill level
2. Unexpected Events
3. Efficiency of work time
4. Mistake and misunderstanding
5. Common cause Variation
2. Six Methods for Estimating Activity
Duration
• Similarity to other activities
• Historical data
• Expert advice
• Delphi technique
• Three point technique
• Wide-band Delphi technique
6. THREE POINTS TECHNIQUES
The three points technique gives us a
framework for doing just that. To use the
method, you need three estimates of activity
duration:
OPTIMISTIC. The optimistic time is defined as
the shortest duration one has had or might
expect to experience given that everything
happens as expected.
7. THREE POINTS TECHNIQUES
• PESSISMISTIC. The pessimistic time is that duration
that would be experienced ( or has been
experienced) if every thing that could go wrong did
go wrong, yet the activity was completed.
• MOST LIKELY. The most likely time is that time
usually experienced.
9. APPLYING THE WIDE-BAND DELPHI
TECHNIQUES
Combining the Delphi and three-point methods
results in the wide-band Delphi techniques. It
involves a panel. As in the Delphi technique. In
place of a single estimate the panel members are
asked, at each iteration, to give their single
estimates for the duration of the chosen activity.
The results are computed for each of the three
estimates, and the averages are used the
optimistic, pessimistic, and most likely estimates
of activity duration.