What is the difference between Analogous Estimating and Parametric Estimating?
Planning, in particular, project cost and time planning, requires a lot of estimation as the work involved has not happened yet. In real-world project management, the most common estimating methods are : Analogous Estimating and Parametric Estimating.
These two estimating methods have some similarities and differences.
Analogous Estimating :
Applicable to both time and cost estimating, analogous estimating uses export judgment and historical information to predict the future. It can be done at the project level (e.g, the last five projects similar to this one each took eight months, so this one shoul as well).
Management or the sponsor might use analogous estimating to create the overall project estimate given to the project manager as the project is chartered. It can also be applied at the actevity level, if the activity has been done on previous projects and there is substantial historical data to support the accuracy of such an estimate.
Parametric Estimating :
Parametric estimating looks at the relationships between variables on an activity to calculate time or cost estimates. The data can come from historical records from previous projects, industry requirements, standard metrics, or other sources.
There are two ways a project manager might create parametric estimate :
- Regression analysis (scatter diagram) : This diagram tracks two variables to see if the are related and creates a mathematical formula to use in future parametric estimating.
- Learning curve : Example : The 50th room painted will take less time than the first room because of improved efficiency.
Analogous Estimating vs Parametrics Estimating :
Both Analogous Estimating and Parametric Estimating is based on the historical information from the organization/industry to estimate cost/duration of the project/activity, there are some differences between them:
- Analogous Estimating is considered a top-down approach which is much less accurate than parametric estimating in which Analogous Estimating is based on simple “analogy”;
- Parametric Estimating is more accurate for projects/activities with components which are similar and “scalable”, it is based on a unit cost/duration of historical data which is scaled to give the estimation;
- Analogous Estimating is used early in the project where there are only limited amounts of information available while Parametric Estimating is used if the project/activity is “scalable”.
- Analogous estimating is generally less costly, time consuming than parametric estimating but less accurate.
Other estimation methods:
One-Point Estimating :
When estimating time using a one-point estimate, the time estimate may be based on expert judgment of historical information, or it could be just a gess which make this method problematic.
Three-point estimating :
This method/technique is used when a project manager comes with three numbers : a most likely estimate (M) that probably will happen, an optimistic one that represents the best-case scenario (O), and a pessimistic one that represents the worst-case scenario (P). The final estimate is the average.
PERT (Program Evaluation Review Technique) is the most common form of three-point estimation. It’s a technique that was developed in the 1960’s by consulting firms working with the U.S government as a way of getting more accurate project duration prediction up front.
Triangular Distribution (Simple Average):
In this method, a simple average of three-point estimates can be done using the forula (P + O + M)/3. Using this method, the risks (P and O estimates) are considered equally along with the most likely (M) estimate.
Bottom-up Estimating (definitive technique) :
It is the most accurate and time-consuming of all estimation methods in which every single activity is broken down into details at the bottom level and aggregate the estimations of each individual components to give an overall estimation.