smart_distpars generates random degrees of freedom parameter values
  close to given values.
smart_distpars(distpars, accuracy, cond_dist)Returns a numeric vector ...
cond_dist == "Gaussian":of length zero.
cond_dist == "Student":of length one containing a degrees of freedom parameter value (strictly larger than two).
cond_dist == "ind_Student":of length d containing a degrees of freedom parameter values (strictly larger than two).
cond_dist == "ind_skewed_t":of length 2d containing df params strictly larger than two in the first d elements and skewness params strictly between -1 and 1 in the rest d elements.
the old distribution parameters (of all regimes)
a positive real number adjusting how close to the given distribution parameters the returned values should be.