dev.nm.stat.descriptive.moment

Class Mean

java.lang.Object

dev.nm.stat.descriptive.moment.Mean

All Implemented Interfaces:

Statistic

public class Mean
extends Object
implements Statistic

The mean of a sample is the sum of all numbers in the sample, divided by the sample size. That is, \[ \bar{x} = \frac{1}{N}\sum_{i=1}^{N}x_i \] This implementation supports incremental update of the statistic.

The R equivalent function is mean.

Batch and incremental use

addData(double...) appends observations to the accumulated sample; it does not replace earlier observations. N() counts all observations. value() returns Double.NaN before the first observation. Create a new calculator to start a new sample. Empty update batches are ignored, including before the first observation.

Example

 import dev.nm.stat.descriptive.moment.Mean;
 import dev.nm.stat.descriptive.moment.Variance;

 Mean mean = new Mean(new double[]{1, 2});
 mean.addData(3, 4);
 assert mean.N() == 4;
 assert mean.value() == 2.5;
 Variance sample = new Variance(new double[]{1, 2, 3, 4});
 Variance population = new Variance(new double[]{1, 2, 3, 4}, false);
 assert Math.abs(sample.value() - 5.0 / 3.0) < 1e-12;
 assert Math.abs(population.value() - 1.25) < 1e-12;
 

Empty batches in streaming data

Empty batches are safe before, between, and after observations. They do not reset the sample.

 import dev.nm.stat.descriptive.moment.Mean;
 Mean mean = new Mean();
 mean.addData();
 assert Double.isNaN(mean.value());
 mean.addData(3, 5);
 mean.addData(new double[0]);
 assert mean.N() == 2;
 assert mean.value() == 4.0;
 

Constructor Summary

Constructors

Constructor and Description
Mean() Construct an empty Mean calculator.
Mean(double[] data) Construct a Mean calculator, initialized with a sample.
Mean(Mean that) Copy constructor.

Method Summary

Modifier and Type	Method and Description
void	addData(double... data) Appends observations to the current sample.
long	N() Get the size of the sample.
String	toString()
double	value() Returns the arithmetic mean of all observations added so far.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Constructor Detail

Mean

public Mean()

Construct an empty Mean calculator.

Mean

public Mean(double[] data)

Construct a Mean calculator, initialized with a sample.

Parameters:

data - a sample

Mean

public Mean(Mean that)

Copy constructor.

Parameters:

that - a Mean calculator

Method Detail

addData

public void addData(double... data)

Appends observations to the current sample.

Specified by:

addData in interface Statistic

Parameters:

data - observations to add

See Also:

N(), value()

value

public double value()

Returns the arithmetic mean of all observations added so far.

Specified by:

value in interface Statistic

Returns:

the mean, or NaN when the sample is empty

N

public long N()

Description copied from interface: Statistic

Get the size of the sample.

Specified by:

N in interface Statistic

Returns:

the sample size

toString

public String toString()

Overrides:

toString in class Object