This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: A P P E N D I X 1 @Risk Crib Sheet @Risk Icons Once you are familiar with the function of the @Risk icons, you will find @Risk easy to learn. Here is a description of the icons. Opening an @Risk Simulation This icon allows you to open up a saved @Risk simulation. I do not recommend saving simulations. Instead, I paste results into a spreadsheet. Saving an @Risk Simulation This icon allows you to save an @Risk simulation, including data and simulation settings. Simulation Settings This icon allows you to control the settings for the simulation. Clicking on this icon ac tivates the dialog box shown in Figure 1. There follows a description of what each of the tabs can do. Iterations Tab Various options are associated with the Iterations tab. #Iterations #Iterations is how many times you want @Risk to recalculate the spreadsheet. For example, choosing 100 iterations means that 100 values of your output cells will be tabulated. F I G U R E 1 A P P E N D I X 1 @Risk Crib Sheet 1337 #Simulations Leave this at 1 unless you have a RISKSIMTABLE functon in the spread sheet. In this case, choose #Simulations to equal the number of values in SIMTABLE. For example, if we have the formula RISKSIMTABLE({100,150,200,250,300}) in cell A1, set #Simulations to 5. The first simulation will place 100 in A1, the second simulation will place 150 in A1, and the fifth simulation will place 300 in A1. #Iterations will be run for each simulation. Pause on Error Checking this box causes @Risk to pause if an error occurs in any cell during the simulation. @Risk will highlight the cells where the error occurs. Update Display Checking this box causes @Risk to show the results of each iteration on the screen. This is nice, but it slows things down. See Figure 2. The Sampling tab options are as follows. Sampling Type While a little slower, Latin Hypercube sampling is much more accurate than Monte Carlo sampling. To illustrate, Latin Hypercube guarantees for a given cell that 5% of observations will come from the bottom 5th percentile of the actual random vari able, 5% will come from the top 5th percentile of the actual random variable, etc. If we choose Monte Carlo sampling, 8% of our observations may come from the bottom 5% of the actual distribution, when in reality only 5% of observations should do so. When sim ulating financial derivatives, it is crucial to use Latin Hypercube. Standard Recalc If you choose Expected Value, you obtain the expected value of the ran dom variable unless the random variable is discrete. Then you obtain the possible value of the random variable that is closest to the random variable’s expected value. For in stance, for a statement RISKDISCRETE({1,2,},{.6,.4}) the expected value is 1(.6) 2(.4) 1.4, so Expected Value enters a 1....
View
Full
Document
This note was uploaded on 11/02/2010 for the course ORIE 1101 taught by Professor Trotter during the Fall '10 term at Cornell.
 Fall '10
 TROTTER

Click to edit the document details