codecamp iasi 7 mai 2011 monte carlo simulation
TRANSCRIPT
26 October 2010
Monte Carlo Simulation
Constantinescu Eugen
Index1. Motivation and objectives2. Basic Knowledge3. Practical examples4. Conclusions5. Reference Links
Motivation and objectivesMotivation:1. Our estimations from projects are not good enough2. There is place for risks assessment improvement3. This model is closer to reality than the classical one4. Let's try to see our projects from more points of view
Objectives:1. Learn about the basic knowledge MCS2. What are the main benefits from using MCS?3. What we can change?4. Where we can improve?
Basic knowledgeProcess determinist versus process stochastic
Monte Carlo Simulation is a method for iteratively evaluating a deterministic model using sets of random numbers as inputs. This method is often used when the model is complex, nonlinear, or involves more than just a couple uncertain parameters.
Basic knowledgeStep 1: Create a parametric model, y = f(x1, x2, ..., xq).
Step 2: Generate a set of random inputs, xi1, xi2, ..., xiq.
Step 3: Evaluate the model and store the results as yi.
Step 4: Repeat steps 2 and 3 for i = 1 to n.
Step 5: Analyze the results using histograms, summary statistics, confidence intervals, etc.
Basic knowledgeHistograms
Data:
Frequency
Cumulative frequency
Min, Mean (Average), Max
Skewness
Kurtosis
Confidence Interval
Practical examples1.MSP small example
MCS sheets
Analysis
2.MSP real life example
MCS sheets
Analysis
Conclusions1. Learn about the basic knowledge MCS – DONE
Take a look over the MATH behind MCS, or just go to point 2.
2. What are the main benefits from using MCS?CP and PERT (Program Evaluation and Review Technique) are
optimistic estimations => MCS helps for a better planning
3. What we can change?We should focus on the tasks which have highest chance to
become CP. We should start to change the current estimation template and
MSP template so that we can include Min, Most Likely and MAX estimation values.
Conclusions4. Where we can improve?
Identify and define the risks easier (Assessing Risks Improvement )Analyze the tasks which have higher impact into the project costs (See the most sensitive tasks)
Reference Links
1. http://www.vertex42.com/ExcelArticles/mc/MonteCarloSimulation.html
2. http://mathworld.wolfram.com/MonteCarloMethod.html
3. http://rule-of-thumb.net/monte-carlo-simulation-for-ms-project/http://sourceforge.net/projects/montecarloprj/
4. file://storage/IIC-ForAll/08_PM_Community/MCS