Monte Carlo Simulation using Invest Sign

Introduction

The majority of project planning effort today is still performed in a strictly “deterministic” manner. All project tasks and resources are assigned and executed within well defined timeframes. At the same time we all know that real life necessitates corrective actions:

 Resources are not always available

 Extra tasks pop up during the course of the projects

 What happens most frequently is the initial estimate of the time required to perform a certain task is no longer valid

It’s easy to mentally grasp such uncertainties and have an accurate estimate when dealing with a few variables. With large scale projects however having multiple uncertainty factors of a different nature and character means such analysis can not be performed manually. It demands a very special effort for an accurate project assessment.

Project analysis using Invest Sign

Such uncertainty in project planning and risk analysis is widely recognized in a lot of industries and a Invest Sign exists to help optimize the planning, evaluation process and minimize the associated risks. The program allows to describe and formulate your project, idenitify sensivitive key parameters using Sensitivity analysis and use Monte Carlo simulation technique to estimate the impact of risk on the projected results.

There are posibility to use maximum six variables (or groups of variables) for optimization purposes at one time. Invest Sign allows to select destribution from 14 different distributions: Uniform, Beta, Binomial, Chi-squared, Exponential, Gamma, InvGaussian, LogNormal, NegBinomial, Normal, Poisson, Student's "t", Von Mises, Weibull distributions.

Risk evaluation process

Project example, listed below, is used here to illustrate the application of sensitivity analysis. For more information on exporting Monte Carlo simulation data with Invest Sign refer to article How Do I Export Monte Carlo simulation data of Project to .text document?. This example is for teaching purposes to use Invest Sign, so only a few key factors are selected.

The risk analysis process using Invest Sign consists of the 5 main steps:

1. Identify uncertain variables

 Which variables, or their inputs in the plan are uncertain and critical to the viability of the project?

 What we know about these uncertainties?

Using Sensitivity analysis we identified these key variables which are uncertain and critical to the viability of the project: administration wages, direct material cost and the forecast price of network swichers. From past projects experience and “historical” knowledge we defined the possible ranges for different key variables and choosed distribution functions. Direct material costs are described with Student's "t" distribution, Administration wages and Selling price with Normal distributions.

2. Define probability distributions

 What would be the best way to describe these uncertainties?

 What values are considered to be the highest and lowest possible for each variable, what is the known range of values?

 Which distributions describes the each variable?

 What distribution describes the each variable the best?

The detailed parameters are listed below:

Table 1. Direct material costs

Table 2. Administration wages

Table 3. Selling price

3. See the possibility for correlation conditions

 Does the correlations exist among any of the selected risk variables?

 How to diminish these correlations and (or) limit their expected dependency characteristics?

We analysed correlation conditions and saw that direct material costs and selling price of products correlate, so we can expect positive covariance between them. The correlation coeficient is 0,65. It is too low to obtain correlation conditions but exists, so the best way is to limit of their expected dependency characteristics by excluding one of them (direct material costs or selling price of products) from analysis. We excluded selling price of products.

4. Run simulation

As the result of the Monte Carlo simulation (parameters of the simulation are configured too) we can obtain the ranges and probabilities of all outcomes for the outputs that we’ve identified.

The simulation run in Invest Sign is very simple. We push button "Calculate" and simulation runs. When Invest Sign performs calculations then in the bottom of the window reference come: “! Monte Carlo analysis: calculations are made.”

5. Analyse results and make a decision

Based on the simulation results, and looking at the outputs of the model, we obtain the information about most critical characteristics of the project. This data serve as the basis for the following optimization and corrective actions.

 What is degree of probability of the project result that is above or below the value we are interested in?

 Which of these coefficients (expected value, cost of uncertainty, expected loss ratio, variation) we need to calculate?

 What decisions we can make?

Results, graphs, common statistics and generated values and for each variable (variables and NPV) you can look by pushing button “Results” of selected variable or project results.

Tables 4, 5, 6. Results of Project without external sponsorship

The result table with all data of variables using Export menu Export Monte Carlo data command you can display in MS Office program (Excel), or you can export the data and graphs of the selected variable or project results by pushing Save As..., then data will be saved in .txt format.

Invest Sign allows to make analysis in two ways:

 Data and statistics analysis for each variable (needed to ensure that selected model and distributions are correct);

 Data and statistics analysis of project results (the purpose is to calculate coeficients and support decisions).