class GoodnessOfFit_KS extends Error
The GoodnessOfFit_KS
class is used to fit data to a probability distribution.
It uses the Kolmogorov-Smirnov Goodness of Fit Test. Determine the maximum
absolute difference 'd_max' between the data points 'd_i' and the theoretical
value from a CDF F,
d_max = max 1≤i≤n {|Fe(d_i) - F(d_i)|} (concept)
d_max = max 1≤i≤n {F(d_i) − (i−1)/n, i/n − F(d_i)} (calculation)
where 'Fe(.)' is the empirical distribution and 'F(.)' is the theoretical distribution. If 'd_max' is large, the fit should be rejected.
- See also
www.itl.nist.gov/div898/handbook/eda/section3/eda35g.htm ---------------------------------------------------------------------------------
www.eg.bucknell.edu/~xmeng/Course/CS6337/Note/master/node66.html
- Alphabetic
- By Inheritance
- GoodnessOfFit_KS
- Error
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Instance Constructors
Value Members
-
def
fit(cdf: Distribution, parms: Parameters = null): Double
Perform a KS goodness of fit test, matching the CDF of the given data 'd' with the random variable's Cumulative Distribution Function (CDF).
Perform a KS goodness of fit test, matching the CDF of the given data 'd' with the random variable's Cumulative Distribution Function (CDF).
- cdf
the Cumulative Distribution Function to test
- parms
the parameters for the distribution
- See also
www.usna.edu/Users/math/dphillip/sa421.f13/chapter02.pdf
-
final
def
flaw(method: String, message: String): Unit
Show the flaw by printing the error message.
Show the flaw by printing the error message.
- method
the method where the error occurred
- message
the error message
- Definition Classes
- Error