I am not trying to imply that there is something wrong with the method. I just can not make sense of the results. And I am sorry for that.
No worries, I am just trying to get a better understanding of the situation as well.
I mean the function we are running the GSA on. Were you were running Morris on the entire time series of the solution in R as well? Are the timepoints you are trying to compare (at which the solutions are being recorded) the same in both R and Julia?
That’s a little reassuring, was Sobol run for the entire ODE solution as well or on some reduction of the solution?