Risk Analysis Techniques

Risk: Project risk can be defined as any uncalled event or a condition that, if occurs, impacts at least one of the project objectives. 

Risks can either be positive or negative. 

•  Negative risks are unwanted and potentially can cause serious problems      and spoil the project.
•  Positive risks, on the other hand, has a positive effect on the project such    as increasing the Rate of interest or finishing the project ahead of time.
•  Once the risks are identified, we proceed with their analysis. Risk Analysis  determines which risk factors will potentially have a higher impact on the    project and, therefore, should be managed by the stakeholders correctly.

The various techniques for risk analysis are as under:

1.Brainstorming

It is largely used in formative project planning, which helps in identifying and postulating risk scenarios for any given project. 

Process:
Considered as an effective attempt to help people think creatively in a         group without having a fear of being criticized by others. 

• Each member tries to build on the ideas given in preceding comments. 
• Criticism and disapproving verbal or nonverbal behaviors are not allowed. 
• The main intention is to encourage as many ideas as possible, which in turn, triggers the ideas of others.

Best suited - To identify maximum amount of risks possible in a project, as employees build on each other’s ideas, producing much greater output than they would as individuals.

2.Sensitivity Analysis

This is the simplest form of Risk Analysis. 

Process:

• Analysis of the effect of change of a single variable in a project is done, and a corresponding value is placed for the same in the project. 
• This uncovers uncertainty and risks for that project i.e. the sensitivity of the project is exposed.
• Generally, such type of analysis is performed only on those variables which have higher impact on cost and time to which the project is most sensitive.
• Best suited when attempting to determine the actual outcome of a particular variable, if in case it differs from what was previously assumed. The analyst can determine how changes in one variable will impact the target variable by creating different scenarios.
• For example, an analyst might create a financial model that will value a company's equity (the dependent variable) given the amount of earnings per share (an independent variable) the company reports at the end of the year and the company's price-to-earnings multiple (another independent variable) at that time. The analyst can create a table of predicted price-to-earnings multiples and a corresponding value of the company's equity based on different values for each of the independent variables.

Weakness: 
Variables are treated individually, which limits the combinations of variables to be assessed

3.Probability Analysis

Probability analysis overcomes the limitations of sensitivity analysis by mentioning a probability distribution for each variable, and then assessing situations wherein, any or all of these variables can be modified at the same time. 

This analysis answers 3 questions:

     • What can go wrong?

     • Severity of the potential detriment?

     • How likely it is to occur?

        Best suited when companies have a large amount of data.

4.Delphi Method

A panel of experts arrive at a convergent solution to any specific problem, so as to form a consensus of opinion. This is very useful for probability assessments of large and critical risk impacts related to the future. The first and most important step is to select a panel of people who have experience in the area of issue. 

It is advisable that the panel members should not know each other’s identity and hence the selection process should be conducted at different locations.

The responses along with opinions and justifications, are evaluated and a statistical feedback is given to each panel member in the next iteration. The process is ongoing, until group responses converge to any particular solution.

Best suited - For Business Forecasting as forecasts (or decisions) from a structured group of individuals are more accurate than those from unstructured groups. Also decisions are not biased which keeps any one person from having undue influence on the outcome.

5.Monte Carlo

The Monte Carlo method is simulation by means of random numbers. It is a simple yet powerful way of incorporating probabilistic data. 

Basic steps include:

(a) Define a domain of possible inputs.

(b) Generate inputs randomly from a probability distribution over the domain.

(c) Perform a deterministic computation on the inputs.

(d) Aggregate the results.

Monte Carlo method determines best case, most-likely, and worst-case estimates for any given scenario.

Example: 

Consider creating Most-Likely, worst-case and best-case estimates for the duration of a project. For each of the above mentioned scenarios, the project manager lists out the probability of occurrence.

• Most-likely scenario: Duration will be of three days (70% probability), but it can also be completed in two days (10%) or even four days (20%)
• Worst-case scenario: 60% probability of taking six days to finish, a 20%   probability each of being completed in five days or eight days.
• Best-case scenario: 80% probability to complete in four days, 5% probability to complete in three days and a 15% probability to complete in five days
• A series of simulations are performed on the project probabilities using the Monte Carlo Analysis. The simulation is to run for a thousand odd times, and for each simulation, an end date is noted.
• Once the analysis is completed, there would be no single project completion date. Instead a probability curve is formed which depicts the likely dates of completion and the probability of attaining each.
• With the help of this probability curve, the project manager informs the senior management of the expected date of completion. The project manager would choose the date with a 90% chance of attaining it.

Best advised - To use the Monte Carlo simulation to analyze the likelihood of meeting objectives, given project risk factors, as determined by our schedule risk profile. It is very effective as it is built on evaluation of data numerically and no guesswork is involved.

About Author:

Geetika Varma is a consultant in Systems Plus Pvt. Ltd. Within Systems Plus, She actively contributes to the areas of Technology and Information Security. She can be contacted at: geetika.varma@spluspl.com