Simulation Methods

Select Run Simulation on the Distributions & Simulation Analysis Startup Panel - Quick tab and click the OK  button, or click the Run simulation button in the Fit Distributions Results dialog box, or click the OK button in the Design simulation dialog box to display the Simulation Methods dialog box.

Variables. Note that this button is available only if the Simulation Methods dialog box is reached through the Distributions & Simulation Analysis Startup Panel. Click the Variables button to display a standard variable selection dialog box, in which you select the variables for the analysis. Run Simulation analysis expects the input file to be a correlation matrix, which can be created by clicking the Save distribution fit button on the Fit Distribution Results dialog box - Save Fit tab.

Simulation Methods. The Simulation Methods group box contains the available methods for simulating data.  

Monte Carlo. Select the Monte Carlo option button to generate random data from the best fitting distributions while ignoring the correlations between variables.

Latin Hypercube Sampling (LHS). Select the Latin Hypercube Sampling option button to generate random data from the best fitting distributions by the Latin Hypercube method. Similar to the Monte Carlo method, this method also ignores the correlations between variables.

Correlation Based. Select one of the simulation methods in the Correlation Based group box to generate random data from the best fitting distribution while preserving the rank correlations between variables.

Iman Conover. Select the Iman Conover option button to generate random data from the best fitting distributions while preserving the rank correlation structure by the Iman Conover method.

LHS with Iman Conover. Select the LHS with Iman Conover option button to generate random data from the best fitting distributions while preserving the rank correlation structure by the LHS with Iman Conover method.

Options.

Number of samples. Specify the number of random samples to generate.

Seed random number. Select the Seed random number check box and specify a constant value to seed the random number generator.

Truncate simulated values to .5% - 99.5% interval. Select this check box to specify that simulated values will fall between the 0.5th and 99.5th percentiles of the theoretical distribution(s).

Auto update on the current spreadsheet. Select the Auto update on the current spreadsheet check box to generate random numbers into the same spreadsheet for multiple simulation runs.

Simulate. Click the Simulate button to simulate random data according the specifications set in the Simulation Methods dialog.

Cancel. Click the Cancel button to close the dialog box without performing an analysis.

Options. Click the Options button to display the Options menu.