PMI RMP – PERFORM QUANTITATIVE RISK ANALYSIS QUIZ Question part 1

3. TOOLS AND TECHNIQUES

Hi and welcome back again. So what are the tools and techniques we are going to use to quantify our identified project tasks? We need a lot of tools and techniques. This lecture is very important for the PMI Rmp exam. Expect to see like 20 to 25 questions only about about this lecture and the following lecture. Now we will be starting with the most commonly used tool which is the expert judgment. Judgment provides upon expertise as an application area, knowledge area or discipline as appropriate for the activity being performed. And the activity being performed here is the quantitative risk analysis. You will use the experts and their judgment on your organization for the maybe defining the risk probabilities, defining the impact of the top priority risks.

The expert judgment will be very useful in the quantitative risk analysis. We will need also the data gathering techniques and the only data gathering technique we are using here is the interviews. As per the interviews I explained in the Identifiers process, in the qualitative risk analysis process, the same procedure will follow here. It’s a structured or semi structured interviews that can be used as inputs to the quantitative risk analysis in particular way. They are useful when information is required from experts for few critical risks on your project, you need to perform interviews with experts to take their advice about specific probabilities and risks impact.

So this is the only data gathering technique we are using in the quantitative risk analysis process. We will need the interpersonal and team skills. We will need the Facilitation technique which improves the effectiveness of quantitative risk analysis of the individual project risks. Your ability to facilitate the risk workshops, to facilitate the meetings, to manage the expert interviews requires facilitation. Now the fourth tool is the representation of uncertainty where the duration, cost or resources requirements for a planned activity is uncertain, the range of possible values can be represented in a model as a probability distribution. The most commonly used forms are the triangle distribution and the beta distribution.

Now the representation of uncertainty, it is related actually to the duration, cost and resources estimates for specific activities on the project. The meaning of the representation for uncertainty when you say that you have an activity that will take you from 15 to 20 days, this is a representation of uncertainty within the duration estimate of that activity. The most commonly used ones are the triangle distribution and the beta distribution, which I’m going to explain now. Both the triangle and beta distributions refer to the three point estimating and the three point estimating is an estimation technique used in the estimate activity durations process, estimate activity costs and estimate activity resources.

It is based on three estimates that when average come up with a final estimate, the three estimates that you will use are most likely estimates M and the optimistic estimate O and the Pessimistic estimate P. The most likely estimate assumes that there are no disasters and this activity will be performed as planned. Exactly as planned. The optimistic Estimate the other name is the best case scenario estimate.

It’s an estimate or it estimates the fastest time frame in which your resources can complete the activity. And the pessimistic estimate or the worst case scenario estimate assumes the worst happens and it takes much longer than plan to get the activity completed.

These are the three points which are the basis of the three points estimating. Then you can choose to use one of the two formulas to calculate the expected duration estimate or to calculate the expected cost or resources estimate for a specific activity. The first one is called the simple average or the triangle distribution. It consists of summing the optimistic, the most likely and the pessimistic estimates and then dividing the sum by three, usually used when you don’t have enough historical data to assess when the estimates or when the estimates are derived using expert judgment.It’s very simple formula the expected activity duration or the expected activity cost equals the pessimistic plus the most likely plus the optimistic divided by three.

It’s a simple average formula. This is the triangle distribution that we will use to represent the uncertainty. The second one called the beta distribution is taken from the program review and estimation technique Perth. It’s also called the Perth formula. Now, the formula here gives more consideration to the most likely estimate. It’s p plus four m plus O divided by six. You need to memorize these formulas for the exam it is preferred. I’m talking about the beta distribution when you have a good set of historical information and samples to base the estimates on. So the first one is called the triangle distribution or the simple average. The second one is called the beta distribution, the third formula or the weighted average.

Now how to find out the beta standard deviation. That standard deviation refers to the possible range of the estimate it helps you to determine the confidence level. For example, what’s the standard deviation an activity estimate of 50 hours duration that has a standard deviation of plus -3 hours is expected to take between 47 hours in the best case scenario and 53 hours in the worst case scenario plus minus three is called the beta standard deviation. So the expected activity duration plus minus the standard deviation represents the range of estimate that is used as the representation of uncertainty in the quantitative risk analysis process. What’s the formula of finding out the beta standard deviation? It’s p minus o divided by sex.

So the activity range of estimate equals the expected activity duration plus minus the standard deviation and the standard deviation is the semester estimate minus the optimistic estimate divided by six. That means that the range of the estimate starts with the expected activity duration minus the standard deviation. This is the worst case sorry, this is the best case and ends with the expected activity duration plus the standard deviation. And this is the worst case. Now, the relation between the standard deviation and the risk, the higher the standard deviation of an activity, the higher is the uncertainty in this activity because the standard deviation measures the difference between the pessimistic and the optimistic estimates.

A greater spread between these two figures, which results in a higher number, indicates a greater risk within this activity. It’s very important to understand this paragraph. Now, when you are finding out a beta standard deviation for an activity, either you are calculating the resources, the durations or the cost. The higher the difference between the pessimistic and the optimistic estimate, the higher the standard deviation value and the higher the risk associated with this activity. This is the most important part to understand. Here’s an example, an activity on your project with an optimistic duration estimate of 28 days.

The best case scenario estimate is 28 days and the pessimistic or the worst case estimate is 52 days. Knowing that the most likely estimate of activity is 30 days, what’s the activity range of estimate? So PM and o are all given in the question. First of all, you need to find out the expected activity duration by applying the perk formula or the beta project duration. It’s the pessimistic plus four by the most likely plus the optimistic divided by six. So it’s 52 plus four by three plus 28 divided by six. So the expected duration is 33. 33 days. To find out the range of estimate as requested in the question, you need to calculate the beta standard deviation.

The formula is p minus zero divided by six so it’s 52 -28 divided by six. It equals 24 by six divided by six, so it’s four days. So what’s the range of estimate for this activity? It’s the expected activity duration plus minus the standard deviation 33 plus minus four. So in the best case, this activity can be completed in 29. 33 days. In the worst case scenario, this activity will be completed in 37. 33 days. This is the representation of uncertainty. When this number is higher, the higher is the risk associated with this activity. We have the data analysis techniques and the most important one is the simulation. Actually, the simulation technique is the core technique applied in the quantitative risk analysis.

In this process, you will use models that simulates the combined effects of individual project risks and other sources of uncertainty to evaluate their potential impact on specific project objectives. The most commonly used simulation technique is called the Monte Carlo simulation. It’s a computer software used to iterate the quantitative risk analysis 1000 times. So the Monte Carlo simulation is the most commonly used simulation technique when it comes to the performed quantitative risk analysis process. The Monte Carlo simulation involves determining the impact of the identified risks by running multiple and random simulations to identify the range of possible outcomes for a number of scenarios.

Random sampling is performed by using uncertain risk valuable inputs. Usually these inputs are cost estimates or duration estimates to generate the range of outcomes with a confidence measure for each outcome. So simply using the Monte Carlo simulation, having clear risk variable inputs to this software will give you a specific probability of completing the project on a specific date or on completing the project on a specific budget. This is what we will have once we are done with this simulation. We will have this graph as an output of the Monte Carlo simulation. This was done for the project budget, for the project coast budget, the range of uncertainty for this project that the project budget can be completed with 2 million and it can be completed with 2. 80 million.

Now, what’s the probability of completing the project with 2. 45 million? It’s 85%. So the probability of completing this project with a budget of 2. 5 million or less is 85%, or the probability of completing this project with 2. 2 million is 23%. These are the results of the Monte Carlo simulation when it’s applied on the project cost budget. Here is an example, a simple example that will make the Monte Carlo simulation clear for you. Let’s assume you are managing a project involving a creation of an Elearning module. The creation of the Elearning module comprises of three tasks. So this project, which is the creation of an Elearning module, includes three tasks.

The first one is the writing content, the second task is the creating graphics and the third one is the multimedia integration. Based on previous projects and expert interviews, you determine the best case, which is the optimistic, the most likely and the worst case or the pessimistic of the tasks or activities estimated as follow. The writing content activity can be completed in a range of between four days and eight days creating graphics with five days optimistic, seven days most likely and nine days pessimistic the multimedia integration with two days best case, four days most likely and six days the worst case. So as a total, the best case scenario for this project is to have the best case scenario for each activity.

So if the writing content activity was completed with the optimistic estimate and the creating graphics in addition to the multimedia integration, this project can be completed with only eleven days, while the worst case scenario is eight plus nine plus six, which is 23 days. What can I understand from this table? This project can be completed in any time between the eleven days duration and the 23 day duration can be completed within eleven days with twelve days, with 13 days, with 14 days, with 15 days or with 23 days. So what we’ll do, what we will do with the Monte Carlo simulation, we will get the Monte Carlo simulation.

These variables as inputs, the Monte Carlo simulation will perform 500 or 1000 runs taking random numbers from this table, let’s assume the lighting content with four the creating graphics with five, the multimedia integration with four, what will be the project duration again, the writing content with six, creating graphics with seven, and multimedia integration with two. What will be the duration? And so on. These are the simulation ones that will be performed by the Monte Carlo simulation software. All the results should fall in between the eleven days and 23 days. But applying the Monte Carlo simulation software will give you a specific percentage of the probability of completing the project with 19 days, or with completing the project with 13 days, and so on.

So the Monte Carlo simulation randomly selects inputs, values for the different tasks to generate the possible outcomes. Assuming the simulation in our case or in our example is run 500 times from the previous table, we can see that the project can be completed anywhere between the eleven and 23 days. As I explained for you, the best case is the sum of the best case for each activity, and the worst case the same. It will be in between eleven and 23 days. When the Monte Carlo simulation plans are performed, we can analyze the percentage of time each duration outcome between eleven and 23 is obtained. The following table depicts the outcome of this simulation.

So, here is the output of the Monte Carlo simulation with the data or the input data was chosen randomly for 500 tons for 500 times. Here are the results. So, what’s the probability of completing the project with eleven days? It’s only one person. The project of completing the probability sorry, of completing the project with 15 days or less is 25% only, while the probability of completing the project with 20 days or less is 95%, and so on. This is the result of the Monte Carlo simulations. These results, as shown in front of you now in the table, can be represented as an S graph. Now, what the previous table and below graph or chart suggests is that, for example, the likelihood of completing the project in 17 days or less, here is the 17 days or less is around 33%.

Given this information clocks much more likely that the project will end up taking anywhere between 19 and 20 days, which is 85 and 90%. I hope this example is clear for you. I’m going to explain more examples in the coming lecture about the Monte Carlo simulation. Now, what are the key benefits of using the Monte Carlo simulation? First of all, it’s an easy method for arriving at the likely outcome for an uncertain event and an associated confidence limit for the outcome. Your senior management and the executive management of the organization will have a confidence level about the project or about meeting the project objectives.

If the customer or the senior manager asks you what’s the probability of completing the project on the planned date, you can give the customer a figure, a percentage. So this customer or the senior manager will have a confidence on the project results. Simulations are typically useful while analyzing cost and schedule. With the help of Monte Carlo analysis, you can add the cost and schedule risk variables or risk events to your forecasting model. With a greater level of confidence, the Monte Carlo simulation will consider the risk variables of the schedule durations and the project budget. Useful Technique the Monte Carlo simulation is a useful technique for easing the decision making based on numerical data.

To back up your decision. It can be used to find the likelihood of meeting your project milestones and intermediate goals. So even for the milestone list, for a given milestone in your project, you can have the probability or the likelihood of meeting this milestone. Now, what are the steps you need to follow while performing the Monte Carlo analysis? First of all, the identification of the project risk variables. What are the risk variables you are going to study or you are going to use in the Monte Carlo simulation software? The risk variables for the schedule, for the duration, for the resources requirements. A risk variable is a parameter which is critical to the success of the project and slight variation in its outcome might have a negative impact on the project.

This is the definition of the risk variable you need to identify as the first step of performing the multicolor assimilation. The project risk variables are typically isolated using the sensitivity and uncertainty analysis. I’m going to explain the sensitivity analysis in a few minutes. Sensitivity analysis is used for determining the most critical variables in the project. This is the value of using the sensitivity analysis technique. Uncertainty analysis involves establishing the suitability of a result and it helps in verifying the fitness or validity of particular variable. The second step will be the identification of the range limits for the project variables.

Now you defined or you identify the project variables in the previous step. In this step, you need to identify the range limits of these variables. This process includes defining the maximum and the minimum values for each identified project risk variable. The best way to get these values is using historical data for similar projects. If not, you should rely on expert judgment to determine the most likely values. So it’s important to define the minimum and the maximum figures for each rest variable. The third step will be the specification of probability weights for the established range values. It’s the time to allocate the probability of currents for the project risk variable.

To do so, multival probability distributions are deployed. Commonly used probability distributions for analyzing risks are normal distribution, uniform distribution, triangle distribution, and step distribution. I explained the triangle distribution earlier. This is the most important one the triangle and the beta distribution. Then you need to establish the relationships for the correlated values. If there are any risk variables that have a correlation, you need to consider this as an input for the Monte Carlo simulation software. This step involves defining the correlation between the project risk variables. What’s the correlation is the relationship between two or more variables where a change in one variable includes change and other.