class GoodnessOfFit_CS2 extends Error
The GoodnessOfFit_CS2 class is used to fit data to probability distributions.
Suggestions: each interval should have 'E_i = n*p_i >= 5' and intervals >= sqrt (n).
It uses the Chi-square goodness of fit test with equal probability intervals.
- See also
www.eg.bucknell.edu/~xmeng/Course/CS6337/Note/master/node66.html Compute the following for each interval and sum over all intervals. (O_i - E_i)^2 / E_i where O_i and E_i are the observed and expected counts for interval 'i', respectively.
- Alphabetic
- By Inheritance
- GoodnessOfFit_CS2
- Error
- AnyRef
- Any
- Hide All
- Show All
- Public
- Protected
Instance Constructors
- new GoodnessOfFit_CS2(d: VectorD, dmin: Double, dmax: Double, iCDF: Distribution, parms: Parameters = null, intervals: Int = 10, makeStandard: Boolean = true)
- d
the sample data points
- dmin
the minimum value for d
- dmax
the maximum value for d
- iCDF
the inverse Cumulative Distribution Function
- parms
the parameters for the ICDF
- intervals
the number of intervals for the data's histogram
- makeStandard
whether to transform the data to zero mean and unit standard deviation
Value Members
- def equalProbabilityInterval(intervals: Int): VectorD
Determine the interval end-point values for the "equal probability" interval case.
Determine the interval end-point values for the "equal probability" interval case.
- intervals
the number of intervals
- def fit(met: Metric = pearson): Boolean
Perform a Chi-square goodness of fit test, matching the histogram of the given data 'd' with the random variable's probability function pf (pdf).
Perform a Chi-square goodness of fit test, matching the histogram of the given data 'd' with the random variable's probability function pf (pdf).
- met
the discrepancy metric to use (defaults to pearson)
- final def flaw(method: String, message: String): Unit
- Definition Classes
- Error