Original subtitles

Hello, everyone, and welcome to Part 2 of Session 4 in PMGT 823, Project Risk

Management. In Part A, we focused on qualitative risk analysis, how to

and prioritize risks based on expert judgment and experience.

Now, in Part B, we will take things a step further with quantitative risk

analysis. We will explore how to use numerical tools and models to estimate

overall impact of risks on project outcomes. Let's get started.

In this part of the module, we will focus on quantitative risk analysis.

Unlike qualitative analysis, which is based on judgment and prioritization,

approach uses numerical methods to measure overall risk exposure.

We will look at techniques like expected monetary value, decision tree analysis,

and Monte Carlo simulation.

So if you are ready to dive into some numbers, let's go.

Let's return to the full risk management process to see where quantitative risk

analysis fits in.

After planning for risk management, identifying risks, and performing a

qualitative analysis, finally we arrive at step four that is highlighted here.

This step uses numerical methods to estimate the combined effects of the

on overall project objectives.

It is especially helpful when decisions involve significant costs, timelines, or

resource trade -offs similar to the previous part we have two

important questions here what exactly is quantitative data and why is it

important in risk analysis well quantitative data is information you can

count or verify unlike qualitative data like i drink coffee every day

quantitative data tells us exactly how much or how often

For example, I drink four cups of coffee per day or consume 80 grams of coffee.

Both of them are measurable numerical statements.

In the context of project risk, we use this kind of data to analyze the

impact of all risks on project objectives, such as total cost,

variance, or potential delays.

So one more time, what is the real benefit of using quantitative risk

It gives us a clearer picture of our overall risk exposure and it helps us

better informed decisions about the risk responses.

Quantitative risk analysis has two main benefits.

First, it is the only reliable method for assessing the overall level of

risk because it evaluates the combined impact of all risks and uncertainties.

Second, it gives us quantitative data that supports smarter decision -making.

With this data, we can identify which risks deserve more attention and how we

should respond to them, whether it is setting aside more budget, adjusting

schedules, or preparing contingency plans.

But to do this properly, we need a few things.

First, we need high -quality risk data.

we also need a clear baseline for scope, schedule, and cost.

And of course, sometimes we even need specialized software or expert support

build and interpret models.

So when should you actually perform quantitative risk analysis?

It is best suited for large or complex projects, projects with contractual

requirements, or where stakeholders explicitly request it.

You should also consider it when the project is strategically important for

organization or if it is sensitive to delays and overruns.

But even in these cases, you need to check a few things before jumping in.

So say yes to quantitative analysis if you have the necessary tools and data.

You're confident that most key risks have been identified.

You have budget and time for the analysis, and there is low tolerance for

or schedule deviations.

On the other hand, if your data isn't accurate or subjective inputs work just

well for you, then a qualitative approach might be more efficient and

-effective.

Here is the big picture of the quantitative risk analysis process.

On the left, we start with a solid set of inputs.

including the project management plan, risk register, and reliable cost and

schedule estimates.

Without these inputs, the analysis simply won't work.

In the center, we see a range of tools and techniques used to perform the

analysis. These include expert judgment and interviews, visual models like

influence diagrams, and most importantly, simulation tools,

analysis, and decision tree analysis.

We will cover each of these in more detail in upcoming slides.

Now let's look at the main tools and techniques used in quantitative risk

analysis. We usually begin with the expert judgment, which plays a crucial

especially when translating qualitative insights into numeric estimates or when

interpreting complex results.

Next, we have data gathering, often done through interviews with SMEs to get

accurate data on risk probabilities, impact, and dependencies.

Team skills are also vital because they help ensure the group state focus,

minimize conflict, and support consensus building during risk workshops.

Then we come to the representation of uncertainty.

Here, we model uncertainties in things like cost or time using probability

distributions such as triangular, normal, or beta distributions.

And finally, we use data analysis techniques such as simulations to

wide range of possible outcomes, sensitivity analysis to see which

have the biggest impact,

Decision tree analysis to compare different options under uncertainty and

influence diagrams to show how variable and decisions interact visually.

Let's now look at one of the most powerful tools in quantitative risk

that is Monte Carlo simulation.

This method allows us to evaluate how uncertainties in cost or time might

the overall project outcomes.

Here is how it works.

We take input values like cost estimates or activity durations and let the

computer randomly select values from their defined range.

Then we run the model thousands of times and what we get as outputs are things

like histograms showing the frequency of different results such as how often we

finish under budget.

And also S -curves, which gives us the cumulative probability of meeting a

specific cost or a scheduled target.

For example, if your S -curve shows that there is only a 60 % chance of

completing project under $10 million, then it might be a red flag for you.

And also, when we apply simulation to a scheduled risk, we can do a critical

analysis to find out which activities are most likely to appear on the

parts of the project.

And here we have decision tree analysis that is a valuable tool for choosing the

best option when faced multiple project passes.

Each branch of the tree represents a decision or a chance event.

For example, in this case, we are deciding whether to build a new plant or

upgrade the existing one.

The branches continue with possible future events like a strong or weak

And each endpoint shows the resulting outcomes that can be either a gain or

loss. Then to evaluate each branch, we use expected monetary value or EMV,

is the weighted average of all possible outcomes along that path.

For example, in this case, the decision to build a new plant leads to higher

EMV. So that becomes the optimal choice.

Now let's walk through this example.

Imagine you are prime contractor of the project and the contract imposes a $1

,000 penalty per day of late delivery.

Now you have two subcontractor options.

Subcontractor A is the low -cost but risky option.

They offer a cheaper bid, but there is a 50 % chance of a 90 -day delay, which

could cost you $90 ,000 in penalties.

On the other hand, Subcontractor B is more expensive but more reliable.

They have only a 10 % chance of being 30 days late, meaning a smaller penalty

that is $30 ,000.

So how do you decide?

You will use Expected Monetary Value or EMV. For each option, you combine the

original bid with the probability -weighted penalty to get the expected

cut. Let's see how it works.

Now let's look at how we calculate the expected monetary value for each option.

First, we start with subcontractor A that is low but risky choice.

There is a 50 % chance of a $90 ,000 penalty so the total cost could go up to

$200 ,000.

But there is also a 50 % chance of no delay keeping the total cost at $110

As a result, the EMV here that is the weighted average will be $155 ,000 for

this subcontractor.

Next, we evaluate the subcontractor B that is high but reliable one.

With 10 % chance of a 30 -day delay, the total cost could raise up to $170 ,000.

But in 90 % of the time, there is no delay and the cost stays at $140 ,000.

So EMV will be $143 ,000 for this subcontractor.

As a result, although subcontractor B has a higher bid, its lower risk results

in more favorable expected monetary value.

Therefore, subcontractor B is a smarter choice in terms of minimizing expected

cost.

Now let's talk about influence diagrams, which are powerful tools for analyzing

decisions under uncertainty.

They help us visualize relationships between three key elements that are

decisions, like whether or not to invest on certain factors like R &D success

and outcomes such as sales and net profit.

These diagrams uses arrows to show how different elements influence each other.

For example, here we see that our R &D investment decision affects the

likelihood of R &D success, which in turn influence both sales and net

These models often use probability distribution to represent uncertainty

evaluated using simulation tools like Monte Carlo.

FMEA, or failure moods and effects analysis, is a structured approach that

us identify potential failures in a process, product, or system, and

how these failures might affect overall performance.

The key goal of FMEA is to prioritize risk.

There is done using formula called risk priority number or RPN.

RPN multiplies three factors that are severity or how serious the impact of

would be, occurrence or how likely it is to happen, and detection or how likely

we are to notice the risk before it happens.

Each of these factors is scored on a scale from 1 to 10 and by multiplying

scores together we get an RPN between 1 and 1000.

Higher RPN values mean more critical risks which should be addressed first.

Here we apply the FMEA technique to a real world ID project that is the

implementation of a new CRM system.

Imagine during the risk identification phase the team highlighted three major

risks. that are inadequate training for end users, delays in server delivery by

the supplier, and data transfer errors from the legacy system.

For each risk, we assessed the severity, occurrence, and detectability on a

scale from 1 to 10 and then calculated the risk priority number.

The results show that data transfer errors had the highest RPN of 315.

This means it is the most critical risk and should be addressed first in our

mitigation plans.

The other two risks that are inadequate training with an RPN of 210 and server

delay with an RPN of 96 are still important but with lower priority.

One of the most important outcomes of quantitative risk analysis is the risk

report. This report gives us a clear data -driven picture of the project's

overall exposure to risk using both numerical results and narrative

It also helps us update the key project documents including the overall risk

exposure, detailed probabilistic analysis, and a prioritized list of

risks. In addition, we can track trends across analysis results and determine

which risk response are most appropriate.

Before our next session, please make sure to complete the following readings.

Start with chapters 7 and 9 from Kendrick and also review sections 11 .3

.4 from the PEMBOX 6th edition.

To reinforce your learning, please complete the following activities.

First, reply to at least two of your classmates' posts on Discussion Board 2.

Then take Quiz 3, complete Problem 1, and submit Project Milestone 3.

Finally, please take a few minutes to review the Case Study 4.

And that brings us to the end of Part B of our session on Quantitative Risk

Analysis. If you have any questions, please don't hesitate to reach out. You

also email me.

Thank you very much for watching this video