Thank you very much for your answer Rolf. It helped.
I try to simulate a trade indicator model from market microstructure, where the
1 or -1 indicate a buyer or seller initiated trade respectively.
I use a Gaussian copula for simulation, so I can put in some correlation if I
want to. So I gene
I have no idea what your code is doing, nor why you want correlated binary
variables. Correlation makes little or no sense in the context of
binary random
variables --- or more generally in the context of discrete random variables.
Be that as it may, it is an easy calculation to show that if
Hi R-fellows,
I am trying to simulate a multivariate correlated sample via the Gaussian
copula method. One variable is a binary variable, that should be
autocorrelated. The autocorrelation should be rho = 0.2. Furthermore, the
overall probability to get either outcome of the binary variable sho
3 matches
Mail list logo
