1． Sensitivity Analysis
Sensitivity analysis—the analysis of changes made to significant variables in order to determine their effect on a planned course of action.
Method
Sensitivity analysis has TWO steps:
Step 1 Calculate the NPV of the project on the basis of best estimates.
Step 2 For each element of the decision (cash flows, cost of capital), calculate the change necessary for the NPV to fall to zero.*
Advantages
---It gives an idea of how sensitive the project is to changes in any of the original estimates.
---It directs management attention to checking the quality of data for the most sensitive variables.
---It identifies the critical success factors for the project and directs project management.
---It can be easily adapted for use in spreadsheet packages.
Limitations
Although it can be adapted to deal with multi-variable changes, sensitivity analysis is normally used to examine what happens when one variable changes and others remain constant.
It assumes data for all other variables is accurate. Without a computer, it can be time-consuming. Probability of changes is not considered.
2．Simulation
Stages in a Monte Carlo Simulation
---Specify the major variables.
---Specify the relationship between the variables.
---Attach probability distributions to each variable and assign random numbers to reflect the distribution.
---Simulate the environment by generating random numbers.
---Record the outcome of each simulation.
---Repeat the simulation many times to obtain a probability distribution of the possible outcomes.
Advantages
---It gives more information about the possible outcomes and their relative probabilities.
----This data can be used to calculate an expected NPV (and the standard deviation of the expected NPV).
Limitations
---It is not a technique for making a decision, only for obtaining more information about the possible outcomes.
---It can be very time-consuming without a computer.
---It could prove expensive in designing and running the simulation, even on a computer.
---Simulations are only as good as the probabilities, assumptions and estimates used.