java.lang.Object
- jasima.core.statistics.SummaryStat

All Implemented Interfaces:

Serializable, Cloneable

Direct Known Subclasses:

QuantileEstimator, SamplingSummaryStat, TimeWeightedSummaryStat
```
public class SummaryStat
extends Object
implements Serializable, Cloneable
```
Class to collect the most important statistics without having to store all values encountered. It can return mean, standard deviation, variance, min, max etc. in O(1) time. Values are passed by calling the value(double) method. Values can be weighted, just call value(double, double) instead.
In other simulation packages this is sometimes called "tally".
This implementation is based on: D. H. D. West (1979). Communications of the ACM, 22, 9, 532-535: Updating Mean and Variance Estimates: An Improved Method

Author:

Torsten Hildebrandt

See Also:

Serialized Form

Field Summary

Fields
Modifier and Type Field Description

protected static double DEF_ERROR_PROB

protected double lastValue

protected double lastWeight

Constructor Summary

Constructors
Constructor Description

SummaryStat()

SummaryStat(SummaryStat vs)
Create a new SummaryStat-object initialized with the values of "vs".

Method Summary

All Methods Static Methods Instance Methods Concrete Methods
Modifier and Type	Method	Description
`void`	`clear()`	Resets this object.
`SummaryStat`	`clone()`	Clones this object.
`SummaryStat`	`combine(SummaryStat other)`	Combines the data in `other` with this SummaryStat-Object.
`static SummaryStat`	`combine(SummaryStat stats1, SummaryStat stats2)`	Creates a new `SummaryStat` object that behaves if all values seen by `stats1` and `stats2` would have been passed to it.
`double`	`confidenceIntervalLower()`
`double`	`confidenceIntervalLower(double errorProb)`
`double`	`confidenceIntervalUpper()`
`double`	`confidenceIntervalUpper(double errorProb)`
`double`	`confIntRangeSingle(double errorProb)`
`double`	`lastValue()`	Returns the last value passed to `value(double)` or `value(double, double)`.
`double`	`lastWeight()`	Returns the weight of the last value passed to `value(double)` or `value(double, double)`.
`double`	`max()`	Returns the maximum value seen so far.
`double`	`mean()`	Returns the mean of all values given to `value(double)`.
`double`	`min()`	Returns the minimum value seen so far.
`int`	`numObs()`	Returns the number of times, `value(double)` or `value(double, double)` were called.
`double`	`stdDev()`	The standard deviation of all values.
`double`	`sum()`	Returns the sum of all `value(double)`s (taking into account potential weights if `value(double, double)` is used).
`static SummaryStat`	`summarize(double... values)`	This method creates a new `SummaryStat` object and passes all values to it.
`static SummaryStat`	`summarize(int... values)`	This method creates a new `SummaryStat` object and passes all values to it.
`SummaryStat`	`value(double v)`	Adds the given value with a weight of 1.
`SummaryStat`	`value(double v, double weight)`	Adds a value with a given weight.
`SummaryStat`	`values(double... vs)`	Convenience method to add all values given as arguments with a weight of 1.
`double`	`varCoeff()`	Returns the coefficient of variation (`stdDev()` divided by `mean()`).
`double`	`variance()`	Returns the sample variance of the values.
`double`	`variancePopulation()`	Returns the population variance of the values.
`double`	`weightSum()`	Returns the sum of all weights.

Methods inherited from class java.lang.Object
equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Field Detail
  - DEF_ERROR_PROB
```
protected static final double DEF_ERROR_PROB
```
    See Also:
    
    Constant Field Values
  - lastValue
```
protected double lastValue
```
  - lastWeight
```
protected double lastWeight
```
- Constructor Detail
  - SummaryStat
```
public SummaryStat()
```
  - SummaryStat
```
public SummaryStat(SummaryStat vs)
```
    Create a new SummaryStat-object initialized with the values of "vs". Copy constructor.
- Method Detail
  - clear
```
public void clear()
```
    Resets this object.
  - values
```
public SummaryStat values(double... vs)
```
    Convenience method to add all values given as arguments with a weight of 1.
    
    Parameters:
    
    vs - The values to add.
    
    Returns:
    
    this, to allow easy chaining of calls.
  - value
```
public SummaryStat value(double v)
```
    Adds the given value with a weight of 1.
    
    Parameters:
    
    v - The value to add.
    
    Returns:
    
    this, to allow easy chaining of calls.
  - value
```
public SummaryStat value(double v,
                         double weight)
                  throws IllegalArgumentException
```
    Adds a value with a given weight.
    
    Parameters:
    
    v - The value to add.
    
    weight - The weight to give to this value. Has to be positive.
    
    Returns:
    
    this, to allow easy chaining of calls.
    
    Throws:
    
    IllegalArgumentException - If weight was negative.
  - mean
```
public double mean()
```
    Returns the mean of all values given to value(double).
    
    Returns:
    
    The arithmetic mean of all values seen so far.
  - stdDev
```
public double stdDev()
```
    The standard deviation of all values.
    
    Returns:
    
    The standard deviation of all values given to value(double).
  - variance
```
public double variance()
```
    Returns the sample variance of the values.
    
    Returns:
    
    The (sample) variance of all values given to value(double). Returns NaN, if no values were added yet.
  - variancePopulation
```
public double variancePopulation()
```
    Returns the population variance of the values.
    
    Returns:
    
    The (sample) variance of all values given to value(double). Returns NaN, if no values were added yet.
  - varCoeff
```
public double varCoeff()
```
    Returns the coefficient of variation (stdDev() divided by mean()).
    
    Returns:
    
    The coefficient of variation.
  - sum
```
public double sum()
```
    Returns the sum of all value(double)s (taking into account potential weights if value(double, double) is used).
    
    Returns:
    
    The sum of all values.
  - weightSum
```
public double weightSum()
```
    Returns the sum of all weights. If only value(double) is used, then the value returned is identical to the value returned by numObs.
    
    Returns:
    
    The weight sum.
  - numObs
```
public int numObs()
```
    Returns the number of times, value(double) or value(double, double) were called.
    
    Returns:
    
    The number of calls to value(double) or value(double, double).
  - min
```
public double min()
```
    Returns the minimum value seen so far.
    
    Returns:
    
    The minimum value seen so far, or NaN, if no values were given so far.
  - max
```
public double max()
```
    Returns the maximum value seen so far.
    
    Returns:
    
    The maximum value seen so far, or NaN, if no values were given so far.
  - combine
```
public SummaryStat combine(SummaryStat other)
```
    Combines the data in other with this SummaryStat-Object. The combined object behaves as if it had also seen the data of "other".
    
    Parameters:
    
    other - The SummaryStat to combine with this object.
    
    Returns:
    
    Returns this to allow easy chaining of calls.
  - clone
```
public SummaryStat clone()
```
    Clones this object. We can use the standard functionality here, as there are only primitive fields.
    
    Overrides:
    
    clone in class Object
    
    Returns:
    
    A clone of this SummaryStat.
  - confidenceIntervalLower
```
public double confidenceIntervalLower()
```
    Returns:
    
    lower value of a confidence interval with a 0.95-confidence level
  - confidenceIntervalUpper
```
public double confidenceIntervalUpper()
```
  - confidenceIntervalLower
```
public double confidenceIntervalLower(double errorProb)
```
  - confidenceIntervalUpper
```
public double confidenceIntervalUpper(double errorProb)
```
  - confIntRangeSingle
```
public double confIntRangeSingle(double errorProb)
```
  - lastValue
```
public double lastValue()
```
    Returns the last value passed to value(double) or value(double, double).
    
    Returns:
    
    The last value, or NaN if no numObs==0.
  - lastWeight
```
public double lastWeight()
```
    Returns the weight of the last value passed to value(double) or value(double, double).
    
    Returns:
    
    The last value's weight, or NaN if no numObs==0.
  - summarize
```
public static SummaryStat summarize(double... values)
```
    This method creates a new SummaryStat object and passes all values to it.
    
    Parameters:
    
    values - The values to use.
    
    Returns:
    
    A SummaryStat summarizing the values.
  - summarize
```
public static SummaryStat summarize(int... values)
```
    This method creates a new SummaryStat object and passes all values to it.
    
    Parameters:
    
    values - The values to use.
    
    Returns:
    
    A SummaryStat summarizing the values.
  - combine
```
public static SummaryStat combine(SummaryStat stats1,
                                  SummaryStat stats2)
```
    Creates a new SummaryStat object that behaves if all values seen by stats1 and stats2 would have been passed to it.
    
    Parameters:
    
    stats1 - SummaryStat summarizing first set of values.
    
    stats2 - SummaryStat summarizing second set of values.
    
    Returns:
    
    New SummaryStat object summarizing the union of first and second value set.

Modifier and Type	Field	Description
`protected static double`	`DEF_ERROR_PROB`
`protected double`	`lastValue`
`protected double`	`lastWeight`

Constructor	Description
`SummaryStat()`
`SummaryStat(SummaryStat vs)`	Create a new SummaryStat-object initialized with the values of "vs".

Class SummaryStat

Field Summary

Constructor Summary

Method Summary

Methods inherited from class java.lang.Object

Field Detail

DEF_ERROR_PROB

lastValue

lastWeight

Constructor Detail

SummaryStat

SummaryStat

Method Detail

clear

values

value

value

mean

stdDev

variance

variancePopulation

varCoeff

sum

weightSum

numObs

min

max

combine

clone

confidenceIntervalLower

confidenceIntervalUpper

confidenceIntervalLower

confidenceIntervalUpper

confIntRangeSingle

lastValue

lastWeight

summarize

summarize

combine