Concept: ES Statistical Analysis factors historical variation into the calculation of duration estimates. By analyzing the project’s previous schedule performance, ES stats identify the high and low bounds for the estimate at completion for time. From high/low bounds and target dates, we can determine how well or poorly the project will perform. Thresholds guide the assignment of Green-Yellow-Red status.
Practice: ES metrics such as the Schedule Performance Index for time (SPIt) measure schedule performance. Because they are based on values for past periods and those values are fixed, they offer a precise reading on current performance. Predictions of future schedule performance are not so definitive.
Take the Estimate at Completion for time (EACt). It is easy to calculate and provides a good starting point for assessing what might happen. But, the EACt is limited: it uses the average performance achieved thus far to predict the future, but an average does not take full account of past performance.
As Glen Alleman says, an estimate is not a point value. It is a set of probabilities. Only by factoring in the natural variation in performance over time do we get an accurate fix on the future. That fix is a collection of values determined by statistical analysis of past performance. Fortunately, Walt Lipke has worked out the details of statistical analysis for duration estimates.
If you find the math behind basic ES metrics intimidating, you might fear using ES statistics to manage your schedule. Don’t worry. At ProjectFlightDeck, we commonly use ES Statistical Analysis to steer our projects.* Knowing how to do it, we can tell you what you need to know without going into details of the math.**
In this set of posts, we will first explain in non-technical terms how ES Statistical Analysis works. Then, we will describe how to use it to steer the schedule. Finally, we will illustrate the technique with an example taken from our practice.
Notes:
*ES stats can also be used during the planning stage. Project Planning is a large, complex topic, well beyond the scope of this post. For a good contemporary treatment of the topic, see Alleman (2014). For specifics on the use of ES in planning, see Lipke (2009).
**That said, you really should understand the theory at some point. See Lipke (2009), Lipke (2010), and Lipke (2011).
References
Alleman, G. (2014). Performance-Based Project Management: Increasing the Probability of Project Success. New York, NY: Amacon.
Lipke, W. (2009). Earned Schedule. Lulu.
Lipke, W. (2010). Applying Statistical Methods to EVM Reserve Planning and Forecasting,The Measurable News, Issue 3, 2010.
Lipke, W. (2011). Further Study of the Normality of CPI and SPI(t), PM World Today, October, 2011.
|
