Class SecondMoment
- All Implemented Interfaces:
Serializable
,DoubleConsumer
,AggregatableStatistic<SecondMoment>
,StorelessUnivariateStatistic
,UnivariateStatistic
,MathArrays.Function
The following recursive updating formula is used:
Let
- dev = (current obs - previous mean)
- n = number of observations (including current obs)
new value = old value + dev^2 * (n - 1) / n.
Returns Double.NaN
if no data values have been added and
returns 0
if there is just one value in the data set.
Note that Double.NaN may also be returned if the input includes NaN
and / or infinite values.
Note that this implementation is not synchronized. If
multiple threads access an instance of this class concurrently, and at least
one of the threads invokes the increment()
or
clear()
method, it must be synchronized externally.
- See Also:
-
Field Summary
Modifier and TypeFieldDescriptionprotected double
Deviation of most recently added value from previous first moment.protected double
First moment of values that have been addedprotected double
Second moment of values that have been addedprotected long
Count of values that have been addedprotected double
Deviation of most recently added value from previous first moment, normalized by previous sample size. -
Constructor Summary
ConstructorDescriptionCreate a SecondMoment instance.SecondMoment
(SecondMoment original) Copy constructor, creates a newSecondMoment
identical to theoriginal
. -
Method Summary
Modifier and TypeMethodDescriptionprotected void
aggregate
(org.hipparchus.stat.descriptive.moment.FirstMoment other) Aggregates the results of the provided instance into this instance.void
aggregate
(SecondMoment other) Aggregates the provided instance into this instance.void
clear()
Clears the internal state of the Statisticcopy()
Returns a copy of the statistic with the same internal state.long
getN()
Returns the number of values that have been added.double
Returns the current value of the Statistic.void
increment
(double d) Updates the internal state of the statistic to reflect the addition of the new value.Methods inherited from class org.hipparchus.stat.descriptive.AbstractStorelessUnivariateStatistic
equals, hashCode, toString
Methods inherited from class java.lang.Object
clone, finalize, getClass, notify, notifyAll, wait, wait, wait
Methods inherited from interface org.hipparchus.stat.descriptive.AggregatableStatistic
aggregate, aggregate
Methods inherited from interface java.util.function.DoubleConsumer
andThen
Methods inherited from interface org.hipparchus.stat.descriptive.StorelessUnivariateStatistic
accept, evaluate, incrementAll, incrementAll
Methods inherited from interface org.hipparchus.stat.descriptive.UnivariateStatistic
evaluate
-
Field Details
-
m2
protected double m2Second moment of values that have been added -
n
protected long nCount of values that have been added -
m1
protected double m1First moment of values that have been added -
dev
protected double devDeviation of most recently added value from previous first moment. Retained to prevent repeated computation in higher order moments. -
nDev
protected double nDevDeviation of most recently added value from previous first moment, normalized by previous sample size. Retained to prevent repeated computation in higher order moments.
-
-
Constructor Details
-
SecondMoment
public SecondMoment()Create a SecondMoment instance. -
SecondMoment
Copy constructor, creates a newSecondMoment
identical to theoriginal
.- Parameters:
original
- theSecondMoment
instance to copy- Throws:
NullArgumentException
- if original is null
-
-
Method Details
-
increment
public void increment(double d) Updates the internal state of the statistic to reflect the addition of the new value.- Specified by:
increment
in interfaceStorelessUnivariateStatistic
- Parameters:
d
- the new value.
-
clear
public void clear()Clears the internal state of the Statistic- Specified by:
clear
in interfaceStorelessUnivariateStatistic
-
getResult
public double getResult()Returns the current value of the Statistic.- Specified by:
getResult
in interfaceStorelessUnivariateStatistic
- Returns:
- value of the statistic,
Double.NaN
if it has been cleared or just instantiated.
-
aggregate
Aggregates the provided instance into this instance.This method can be used to combine statistics computed over partitions or subsamples - i.e., the value of this instance after this operation should be the same as if a single statistic would have been applied over the combined dataset.
- Specified by:
aggregate
in interfaceAggregatableStatistic<SecondMoment>
- Parameters:
other
- the instance to aggregate into this instance
-
copy
Returns a copy of the statistic with the same internal state.- Specified by:
copy
in interfaceStorelessUnivariateStatistic
- Specified by:
copy
in interfaceUnivariateStatistic
- Returns:
- a copy of the statistic
-
getN
public long getN()Returns the number of values that have been added.- Specified by:
getN
in interfaceStorelessUnivariateStatistic
- Returns:
- the number of values.
-
aggregate
protected void aggregate(org.hipparchus.stat.descriptive.moment.FirstMoment other) Aggregates the results of the provided instance into this instance.- Parameters:
other
- the instance to aggregate from
-