Presentation is loading. Please wait.

Presentation is loading. Please wait.

UNIVERSITY OF LUSAKA Topic : Risk Assessment-Risk Quantification

Similar presentations


Presentation on theme: "UNIVERSITY OF LUSAKA Topic : Risk Assessment-Risk Quantification"— Presentation transcript:

1 UNIVERSITY OF LUSAKA Topic : Risk Assessment-Risk Quantification
SCHOOL OF GRADUATE STUDIES Topic : Risk Assessment-Risk Quantification Lecture : 6 Lecturer : Eng. M.K.Nsefu

2 Risk Management Tools and Techniques
There are two main categories of RM tools and techniques namely qualitative and quantitative Both tools and techniques can be used at corporate, strategic business and project levels Risk quantification using the impact or the risk matrix assesses two items: the likelihood of an event occurring and the consequence of that event

3 Probability-Impact Grid
This plots the probability of the risk occurring against the impact on the project. They are quantified as high, medium or low – this will give a matrix of nine possibilities. The resulting matrix in this case is a 3 by 3 matrix. The probability- Impact score can be determined by multiplying the impact score and the probability score (see figure below). The weighting of the impact scale serves to focus the risk response on High Impact risk with less weighing given to low probability. The impacts may fall into different levels of severity for any particular risk.

4 Probability-Impact Grid
e.g. risk weighing 9 is the worst risk. The result of this assessment is a ranking for all risks within the project risk register. The outcome from the quantification is prioritising the risk and establishing which risks should be addressed first when generating the risk response plans or allocating project resources .

5 Probability-Impact Grid
3 6 9 2 4 1 3 2 1 Probability Impact

6 Probability-Impact Grid
Probability of Occurrence Low High Low Impact Trivial Expected High Risk Management Hazard

7 Risk Assessment The following are guidelines for making assignments/assessments. Probable—an event will occur several times. Occasional—an event will probably occur sometime. Remote—an event is unlikely to occur, but is possible. Improbable—an event is highly unlikely to occur Catastrophic—results in fatalities, total loss Critical—severe injury, major damage Marginal—minor injury, minor damage Negligible—less than minor injury, less than minor /system damage

8 Risk Assessment Matrix
Severity Catastrophic Critical Marginal Negligible Likelihood Probable High Serious Medium Occasional Low Remote Improbable 16 12 8 4 Occassional 9 6 3 2 1 Weight

9 Likelihood of Occurence
Risk Assessment Likelihood of Occurence 1 2 3 4 5 Severity 6 8 10 9 12 15 16 20 25 Key Low Medium High

10 Risk Analysis with Decision Tree
One of the best ways to analyze a decision is to use so-called decision trees, which makes it possible to see directions that actions might take from various decision points and the decision points relating to it in the future.

11 Risk Analysis with Decision Tree
Decision trees are a simple, but powerful form of multiple variable analysis. They provide unique capabilities to supplement, complement, and substitute for traditional statistical forms of analysis (such as multiple linear regression) a variety of data mining tools and techniques (such as neural networks) recently developed multi-dimensional forms of reporting and analysis found in the field of business intelligence

12 Risk Analysis with Decision Tree
Decision trees are produced by algorithms that identify various ways of splitting a data set into branch-like segments. These segments form an inverted decision tree that originates with a root node at the top of the tree. The object of analysis is reflected in this root node as a simple, one-dimensional display in the decision tree interface. The name of the field of data that is the object of analysis is usually displayed, along with the spread or distribution of the values that are contained in that field.

13 Risk Analysis with Decision Tree
Management are often faced with multiple choices, which in turn are faced with many options. In many cases management only have the resources to opt for one, which presents management with the problem of opportunity cost. However, deciding to adopt an option can be difficult and a useful technique to assess options is the decision tree. This technique explores various investment options available to the decision maker under risk and uncertainty which are graphically represented in the form of sequential decisions and probability events (Merrett and Sykes 1983). PMBOK (1996) describes decision trees as diagrams that depict key interactions between decisions and associated chance events as they are understood by the decision-maker. Decision trees show a sequence of interrelated decisions and the expected outcomes under each possible set of circumstances. Where probabilities and values of potential outcomes are known, they are used as a method of quantification which aids the decision-making process. The aim of the decision tree is to produce an expected value for each option which is the sum of the probabilities and their weighted values. The diagram begins with a decision node at the top of the sheet and consequential chance events and decisions are drawn sequentially as the decision-making process proceeds from top to bottom. Decisions are depicted as square nodes. These are linked by labelled straight lines or ‘branches’ which denote either decision actions if they stem from decision nodes or alternative outcomes if they stem from chance event nodes (Hertz and Thomas 1983, 1984, Gregory 1997).

14 Risk Analysis with Decision Tree
Application Consider a manufacturing company that manufactures milk products. The company is facing challenges of low supply of its products due to increased demand. Consequently, management is considering increasing production using one of the three alternatives A, B and C.The demand for the three alternatives which is 10,000, 20,000 and 50,000 has a demand probability ratio of 0.5,0.3 and 0.2 respectively. The Project Manager upon receipt of this information, he/she must do some risk analysis using the decision tree to come up with the best option to meet the market demand. The Project Accountant has given the figures for Fixed Cost/month, Variable cost and Price per unit. Note that the given figures came up after some accounting computation process. Task: Compute the Risk Analysis using decision tree method with the parameters given by the Project Accountant.

15 Risk Analysis with Decision Tree
Application Consider a manufacturing company that manufactures milk products. The company is facing challenges of low supply of its products due to increased demand. Consequently, management is considering increasing production using one of the three alternatives A, B and C. Option Description Fixed Cost/month Variable Cost Price/ unit Demand Demand Probability A Work Overtime 20,000 9 15 10,000 0.5 B Install New Equipment 80,000 7 0.3 C Rent Machine 35,000 8 50,000 0.2

16 Risk Analysis with Decision Tree
Solution PROFIT PER DEMAND LEVEL Option Price/unit Variable Cost 10,000 20,000 50,000 A Work Overtime 15 9 40000 100000 280000 B Install New Equipment 7 80000 320000 C Rent Machine 8 35000 105000 315000 Profit per demand level is given by: (Demand X Price) - (Demand X Variable Cost + Fixed Cost)

17 Deciding with the Decision Tree
Solution Mothly Profit Demand Probability Expected Value Total Value 40000 0.5 20000 106000 A 100000 0.3 30000 Overtime 280000 0.2 56000 New Equipment Decision B 80000 24000 88000 320000 64000 Rent 35000 17500 C 105000 31500 112000 315000 63000 Calculation 1: Expected value is determined by: monthly profit X probability of occurance Calculation 2: Total value is determined by suming the expected values. The decision to make is one that gives the maximum value. Rent is the best option for this case.

18 Sensitivity Analysis Is a method used to demonstrate the effect on a project, normally in terms of cost or time-to-completion, of changes in variables which are considered to be risks The technique aims to identify the risks which have a potentially high impact on the price/cost, time, profit, NPV and IRR of the project or an investment

19 Sensitivity Analysis Sensitivity Diagrams
Changes and effects are estimated as % of nominal values. Results are plotted on a spider diagram. Variables which have a large effect on contract cost or time can be clearly identified. This analysis is easy to understand and is a good communication tool

20 Sensitivity Analysis Spider Diagram Change in Project Cost, %
Delay in Design 30 20 Energy Cost 10 Change in Variable, % -20 -10 10 20 30 -10 -20

21 Sensitivity Analysis The spider diagram above illustrates the potential changes in variables for a project. In this example 10% increase in energy cost would increase the overall project cost by 5%.

22 Sensitivity Analysis the

23 Sensitivity Analysis The figure above shows another example of plotting the sensitivity analysis. Example: 10% increase in product unit will result in increased sale (£180m), while 10% reduction will result in reduced sales (£78)/ As can be seen above, the sensitivity/spider diagram is a powerful graphical way of looking at information. The diagram represents information produced from a sensitivity analysis and clearly shows the variable to which the project or business is sensitive to.

24 Limitations of Sensitivity Analysis
This analysis does not quantify the probability of risk (e.g. low, medium or high). Risks are treated independently In real life management want to know result of combined effects of changes in variables. Assumes risks occur one at a time and there is no corrective or preventive measures to take in response to any change in risk Assumes small changes are as likely as large changes Above limitations are overcome by probabilistic analysis–Monte Carlo simulation

25 Probability Analysis Probability analysis is a more sophisticated form of risk analysis It overcomes the weaknesses of sensitivity analysis by specifying a probability distribution for each risk and then considering the risks in combination Different values of risk variables are combined in a Monte Carlo Simulation. Frequency of occurrence of variables determined is by defining the probability distribution. Results shown as frequency & cumulative frequency diagrams.

26 Steps in Probability Analysis
Assign a probability distribution to each variable which affects the IRR/NPV. Assign the range of variation for each variable Select a value for each risk variable within its specific range. This is done in such a way that the frequency with which any value is selected corresponds to its probability in the distribution. Carry out a deterministic analysis with the input value selected from specified distributions in random combinations Each time a new value is generated for each variable, a new combination is obtained; hence a new deterministic analysis is done Repeat steps 2 & 3 a number of times. Result: Outcomes arranged in order to form a probability distribution. Accuracy depends on the number of iterations or repetitions, usually 200 iteration sufficient.

27 Cumulative Frequency Diagram
Probability Analysis 100 85% probability that IRR will not exceed 35% 85 15% probability that IRR will not be less than 25% 15 25 IRR % 35 Cumulative Frequency Diagram

28 LIMITATION OF PROBABILISTIC ANALYSIS
You have to do a number of iterations/repeating up to 1000 to come up with the results It is more of a model therefore, results are symptoms of a model and not a project Relies on assumption, need to check the validity of assumptions How accurate is the input data. Outputs depends on the quality of data input?

29 Benefits of Risk Management
Good risk management is known to result into soft as well as hard benefits. Soft Benefits: Improve corporate experience and communication Leads to common understanding and team spirit Assist in distinction between luck and good management Focuses project management attention on real and important issue Facilitates greater risk taking

30 Risk Analysis Risk analysis, or 'probabilistic simulation' based on the Monte-Carlo simulation technique is a methodology by which the uncertainty encompassing the main variables projected in a forecasting model is processed in order to estimate the impact of risk on the projected results. It is a technique by which a mathematical model is subjected to a number of simulation runs, usually with the aid of a computer. During this process, successive scenarios are built up using input values for the project's key uncertain variables which are selected at random from multi-value probability distributions

31 Risk Analysis The simulation is controlled so that the random selection of values from the specified probability distributions does not violate the existence of known or suspected correlation relationships among the project variables. The results are collected and analyzed statistically so as to arrive at a probability distribution of the potential outcomes of the project and to estimate various measures of project risk.

32 Beneficiaries of Risk Management
The following are the beneficiaries of risk management: The organisation-this include corporate and strategic business unit as well as the top management. Clients-both internal and external as they will get what they want when they want it Project Managers-enables managers to deliver projects successfully.

33 Benefits of Risk Management
Good risk management is known to result into soft as well as hard benefits. Hard Benefits: Better and informed plans, schedules, budgets Increased likelihood of adherence to plans Leads to the use of suitable contracts Allows meaningful assessment of contingencies Enables a more objective comparison of objectives Contributes to the build of statistical information Identifies and allocates risks.

34 END


Download ppt "UNIVERSITY OF LUSAKA Topic : Risk Assessment-Risk Quantification"

Similar presentations


Ads by Google