AUTOFIT Subcommand (SIMPLAN command)
The AUTOFIT
subcommand specifies options for automatic
fitting of probability distributions and correlations to fields in
the active dataset.
NCASES. Specifies the number of cases in the active
dataset to be used for automatic fitting of probability distributions
and correlations. For a specification NCASES = n
,
the first n
cases will be used. The default is all
cases.
FIT = AD | KS. Specifies whether to use the Anderson-Darling
or Kolmogorov-Smirnoff test for goodness of fit when automatically
fitting probability distributions for simulated input fields. Only
applies to simulated input fields with a continuous measurement level.
The default is Anderson-Darling (FIT = AD
). For input
fields with ordinal or nominal measurement levels, a chi-square test
is used.
MAXITERATIONS. Specifies the maximum number of iterations SIMPLAN can go through in its computations when automatically fitting probability distributions. The default is 100.
BINS. Specifies the number of bins used when fitting the empirical distribution for a continuous input field. The default is 100 and the maximum is 1000. The empirical distribution is the cumulative distribution function of the historical data.