EViews.com

Hi, I am trying to model the probability of default by a logistic regression using some macro variables as independent variables. The thing is that, after I calibrate the model, I want to perform a Monte Carlo simulation and plot the distribution of the probability of default. As I want to make a use of the model I decided to make 1.000 simulations for each of the variables and then use the coefficients estimated and calculate the prob of default. Is there any way to do the simulations using Eviews 5? I am a bit worried about the error term aswell: if i manage to create the 1000 simulations of the variables in between a given interval, how can I simulate the error term? Should I record the max/min of the error term in the regression, and then generate 1000 numbers in between that interval? Any advice or tip or suggestion would be really appreciated.

You can try the "Model object" in EViews, since it has a built-in simulation property. However, in 5th version you may not be able to save the each scenario. Another way is to use EViews' programming language. For error terms, you can use the random number generator functions of EViews. Since you want to produce 1,000 scenarios, you have to write a loop to handle the repetitions. For details and examples, please refer to manual and search the forum.