You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@commons.apache.org by br...@apache.org on 2007/11/01 12:00:00 UTC
svn commit: r590964 - in /commons/proper/math/trunk:
src/java/org/apache/commons/math/stat/descriptive/
src/test/org/apache/commons/math/stat/descriptive/ xdocs/userguide/
Author: brentworden
Date: Thu Nov 1 03:59:59 2007
New Revision: 590964
URL: http://svn.apache.org/viewvc?rev=590964&view=rev
Log:
set subversion properties on new files.
Modified:
commons/proper/math/trunk/src/java/org/apache/commons/math/stat/descriptive/SynchronizedDescriptiveStatistics.java (contents, props changed)
commons/proper/math/trunk/src/test/org/apache/commons/math/stat/descriptive/SynchronizedDescriptiveStatisticsTest.java (contents, props changed)
commons/proper/math/trunk/xdocs/userguide/stat.xml
Modified: commons/proper/math/trunk/src/java/org/apache/commons/math/stat/descriptive/SynchronizedDescriptiveStatistics.java
URL: http://svn.apache.org/viewvc/commons/proper/math/trunk/src/java/org/apache/commons/math/stat/descriptive/SynchronizedDescriptiveStatistics.java?rev=590964&r1=590963&r2=590964&view=diff
==============================================================================
--- commons/proper/math/trunk/src/java/org/apache/commons/math/stat/descriptive/SynchronizedDescriptiveStatistics.java (original)
+++ commons/proper/math/trunk/src/java/org/apache/commons/math/stat/descriptive/SynchronizedDescriptiveStatistics.java Thu Nov 1 03:59:59 2007
@@ -1,130 +1,130 @@
-/*
- * Licensed to the Apache Software Foundation (ASF) under one or more
- * contributor license agreements. See the NOTICE file distributed with
- * this work for additional information regarding copyright ownership.
- * The ASF licenses this file to You under the Apache License, Version 2.0
- * (the "License"); you may not use this file except in compliance with
- * the License. You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-package org.apache.commons.math.stat.descriptive;
-
-/**
- * Implementation of
- * {@link org.apache.commons.math.stat.descriptive.DescriptiveStatistics} that
- * is safe to use in a mulithreaded environment. Multiple threads can safely
- * operate on a single instance without causing runtime exceptions due to race
- * conditions. In effect, this implementation makes modification and access
- * methods atomic operations for a signle instance. That is to say, as one
- * thread is computing a statistic from the instance, no other thread can modify
- * the instance nor compute another statistic.
- *
- * @since 1.2
- * @version $Revision: 480440 $ $Date: 2006-11-29 01:14:12 -0600 (Wed, 29 Nov 2006) $
- */
-public class SynchronizedDescriptiveStatistics extends DescriptiveStatisticsImpl {
-
- /** Serialization UID */
- private static final long serialVersionUID = 1L;
-
- /**
- * Construct an instance with infinite window
- */
- public SynchronizedDescriptiveStatistics() {
- this(INFINITE_WINDOW);
- }
-
- /**
- * Construct an instance with finite window
- * @param window the finite window size.
- */
- public SynchronizedDescriptiveStatistics(int window) {
- super(window);
- }
-
- /**
- * @see org.apache.commons.math.stat.descriptive.DescriptiveStatistics#addValue(double)
- */
- public synchronized void addValue(double v) {
- super.addValue(v);
- }
-
- /**
- * Apply the given statistic to this univariate collection.
- * @param stat the statistic to apply
- * @return the computed value of the statistic.
- */
- public synchronized double apply(UnivariateStatistic stat) {
- return super.apply(stat);
- }
-
- /**
- * @see org.apache.commons.math.stat.descriptive.DescriptiveStatistics#clear()
- */
- public synchronized void clear() {
- super.clear();
- }
-
- /**
- * @see org.apache.commons.math.stat.descriptive.DescriptiveStatistics#getElement(int)
- */
- public synchronized double getElement(int index) {
- return super.getElement(index);
- }
-
- /**
- * @see org.apache.commons.math.stat.descriptive.DescriptiveStatistics#getN()
- */
- public synchronized long getN() {
- return super.getN();
- }
-
- /**
- * Returns the standard deviation of the available values.
- * @return The standard deviation, Double.NaN if no values have been added
- * or 0.0 for a single value set.
- */
- public synchronized double getStandardDeviation() {
- return super.getStandardDeviation();
- }
-
- /**
- * @see org.apache.commons.math.stat.descriptive.DescriptiveStatistics#getValues()
- */
- public synchronized double[] getValues() {
- return super.getValues();
- }
-
- /**
- * Access the window size.
- * @return the current window size.
- */
- public synchronized int getWindowSize() {
- return super.getWindowSize();
- }
-
- /**
- * @see org.apache.commons.math.stat.descriptive.DescriptiveStatistics#setWindowSize(int)
- */
- public synchronized void setWindowSize(int windowSize) {
- super.setWindowSize(windowSize);
- }
-
- /**
- * Generates a text report displaying univariate statistics from values
- * that have been added. Each statistic is displayed on a separate
- * line.
- *
- * @return String with line feeds displaying statistics
- */
- public synchronized String toString() {
- return super.toString();
- }
-}
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.commons.math.stat.descriptive;
+
+/**
+ * Implementation of
+ * {@link org.apache.commons.math.stat.descriptive.DescriptiveStatistics} that
+ * is safe to use in a mulithreaded environment. Multiple threads can safely
+ * operate on a single instance without causing runtime exceptions due to race
+ * conditions. In effect, this implementation makes modification and access
+ * methods atomic operations for a signle instance. That is to say, as one
+ * thread is computing a statistic from the instance, no other thread can modify
+ * the instance nor compute another statistic.
+ *
+ * @since 1.2
+ * @version $Revision$ $Date$
+ */
+public class SynchronizedDescriptiveStatistics extends DescriptiveStatisticsImpl {
+
+ /** Serialization UID */
+ private static final long serialVersionUID = 1L;
+
+ /**
+ * Construct an instance with infinite window
+ */
+ public SynchronizedDescriptiveStatistics() {
+ this(INFINITE_WINDOW);
+ }
+
+ /**
+ * Construct an instance with finite window
+ * @param window the finite window size.
+ */
+ public SynchronizedDescriptiveStatistics(int window) {
+ super(window);
+ }
+
+ /**
+ * @see org.apache.commons.math.stat.descriptive.DescriptiveStatistics#addValue(double)
+ */
+ public synchronized void addValue(double v) {
+ super.addValue(v);
+ }
+
+ /**
+ * Apply the given statistic to this univariate collection.
+ * @param stat the statistic to apply
+ * @return the computed value of the statistic.
+ */
+ public synchronized double apply(UnivariateStatistic stat) {
+ return super.apply(stat);
+ }
+
+ /**
+ * @see org.apache.commons.math.stat.descriptive.DescriptiveStatistics#clear()
+ */
+ public synchronized void clear() {
+ super.clear();
+ }
+
+ /**
+ * @see org.apache.commons.math.stat.descriptive.DescriptiveStatistics#getElement(int)
+ */
+ public synchronized double getElement(int index) {
+ return super.getElement(index);
+ }
+
+ /**
+ * @see org.apache.commons.math.stat.descriptive.DescriptiveStatistics#getN()
+ */
+ public synchronized long getN() {
+ return super.getN();
+ }
+
+ /**
+ * Returns the standard deviation of the available values.
+ * @return The standard deviation, Double.NaN if no values have been added
+ * or 0.0 for a single value set.
+ */
+ public synchronized double getStandardDeviation() {
+ return super.getStandardDeviation();
+ }
+
+ /**
+ * @see org.apache.commons.math.stat.descriptive.DescriptiveStatistics#getValues()
+ */
+ public synchronized double[] getValues() {
+ return super.getValues();
+ }
+
+ /**
+ * Access the window size.
+ * @return the current window size.
+ */
+ public synchronized int getWindowSize() {
+ return super.getWindowSize();
+ }
+
+ /**
+ * @see org.apache.commons.math.stat.descriptive.DescriptiveStatistics#setWindowSize(int)
+ */
+ public synchronized void setWindowSize(int windowSize) {
+ super.setWindowSize(windowSize);
+ }
+
+ /**
+ * Generates a text report displaying univariate statistics from values
+ * that have been added. Each statistic is displayed on a separate
+ * line.
+ *
+ * @return String with line feeds displaying statistics
+ */
+ public synchronized String toString() {
+ return super.toString();
+ }
+}
Propchange: commons/proper/math/trunk/src/java/org/apache/commons/math/stat/descriptive/SynchronizedDescriptiveStatistics.java
------------------------------------------------------------------------------
svn:eol-style = native
Propchange: commons/proper/math/trunk/src/java/org/apache/commons/math/stat/descriptive/SynchronizedDescriptiveStatistics.java
------------------------------------------------------------------------------
svn:keywords = Date Author Id Revision HeadURL
Modified: commons/proper/math/trunk/src/test/org/apache/commons/math/stat/descriptive/SynchronizedDescriptiveStatisticsTest.java
URL: http://svn.apache.org/viewvc/commons/proper/math/trunk/src/test/org/apache/commons/math/stat/descriptive/SynchronizedDescriptiveStatisticsTest.java?rev=590964&r1=590963&r2=590964&view=diff
==============================================================================
--- commons/proper/math/trunk/src/test/org/apache/commons/math/stat/descriptive/SynchronizedDescriptiveStatisticsTest.java (original)
+++ commons/proper/math/trunk/src/test/org/apache/commons/math/stat/descriptive/SynchronizedDescriptiveStatisticsTest.java Thu Nov 1 03:59:59 2007
@@ -1,39 +1,39 @@
-/*
- * Licensed to the Apache Software Foundation (ASF) under one or more
- * contributor license agreements. See the NOTICE file distributed with this
- * work for additional information regarding copyright ownership. The ASF
- * licenses this file to You under the Apache License, Version 2.0 (the
- * "License"); you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- * http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law
- * or agreed to in writing, software distributed under the License is
- * distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
- * KIND, either express or implied. See the License for the specific language
- * governing permissions and limitations under the License.
- */
-package org.apache.commons.math.stat.descriptive;
-
-import junit.framework.Test;
-import junit.framework.TestSuite;
-
-/**
- * Test cases for the {@link SynchronizedDescriptiveStatisticsTest} class.
- * @version $Revision: 566833 $ $Date: 2007-08-16 15:36:33 -0500 (Thu, 16 Aug
- * 2007) $
- */
-public final class SynchronizedDescriptiveStatisticsTest extends DescriptiveStatisticsTest {
-
- public SynchronizedDescriptiveStatisticsTest(String name) {
- super(name);
- }
-
- public static Test suite() {
- TestSuite suite = new TestSuite(SynchronizedDescriptiveStatisticsTest.class);
- suite.setName("SynchronizedDescriptiveStatistics Tests");
- return suite;
- }
-
- protected DescriptiveStatistics createDescriptiveStatistics() {
- return new SynchronizedDescriptiveStatistics();
- }
-}
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with this
+ * work for additional information regarding copyright ownership. The ASF
+ * licenses this file to You under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ * http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law
+ * or agreed to in writing, software distributed under the License is
+ * distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the specific language
+ * governing permissions and limitations under the License.
+ */
+package org.apache.commons.math.stat.descriptive;
+
+import junit.framework.Test;
+import junit.framework.TestSuite;
+
+/**
+ * Test cases for the {@link SynchronizedDescriptiveStatisticsTest} class.
+ * @version $Revision$ $Date: 2007-08-16 15:36:33 -0500 (Thu, 16 Aug
+ * 2007) $
+ */
+public final class SynchronizedDescriptiveStatisticsTest extends DescriptiveStatisticsTest {
+
+ public SynchronizedDescriptiveStatisticsTest(String name) {
+ super(name);
+ }
+
+ public static Test suite() {
+ TestSuite suite = new TestSuite(SynchronizedDescriptiveStatisticsTest.class);
+ suite.setName("SynchronizedDescriptiveStatistics Tests");
+ return suite;
+ }
+
+ protected DescriptiveStatistics createDescriptiveStatistics() {
+ return new SynchronizedDescriptiveStatistics();
+ }
+}
Propchange: commons/proper/math/trunk/src/test/org/apache/commons/math/stat/descriptive/SynchronizedDescriptiveStatisticsTest.java
------------------------------------------------------------------------------
svn:eol-style = native
Propchange: commons/proper/math/trunk/src/test/org/apache/commons/math/stat/descriptive/SynchronizedDescriptiveStatisticsTest.java
------------------------------------------------------------------------------
svn:keywords = Date Author Id Revision HeadURL
Modified: commons/proper/math/trunk/xdocs/userguide/stat.xml
URL: http://svn.apache.org/viewvc/commons/proper/math/trunk/xdocs/userguide/stat.xml?rev=590964&r1=590963&r2=590964&view=diff
==============================================================================
--- commons/proper/math/trunk/xdocs/userguide/stat.xml (original)
+++ commons/proper/math/trunk/xdocs/userguide/stat.xml Thu Nov 1 03:59:59 2007
@@ -16,7 +16,7 @@
See the License for the specific language governing permissions and
limitations under the License.
-->
-
+
<?xml-stylesheet type="text/xsl" href="./xdoc.xsl"?>
<!-- $Revision$ $Date$ -->
<document url="stat.html">
@@ -28,7 +28,7 @@
<subsection name="1.1 Overview" href="overview">
<p>
The statistics package provides frameworks and implementations for
- basic Descriptive statistics, frequency distributions, bivariate regression,
+ basic Descriptive statistics, frequency distributions, bivariate regression,
and t- and chi-square test statistics.
</p>
<p>
@@ -52,104 +52,104 @@
</ul>
</p>
<p>
- With the exception of percentiles and the median, all of these
- statistics can be computed without maintaining the full list of input
- data values in memory. The stat package provides interfaces and
- implementations that do not require value storage as well as
- implementations that operate on arrays of stored values.
+ With the exception of percentiles and the median, all of these
+ statistics can be computed without maintaining the full list of input
+ data values in memory. The stat package provides interfaces and
+ implementations that do not require value storage as well as
+ implementations that operate on arrays of stored values.
</p>
<p>
- The top level interface is
+ The top level interface is
<a href="../apidocs/org/apache/commons/math/stat/descriptive/UnivariateStatistic.html">
- org.apache.commons.math.stat.descriptive.UnivariateStatistic.</a>
- This interface, implemented by all statistics, consists of
+ org.apache.commons.math.stat.descriptive.UnivariateStatistic.</a>
+ This interface, implemented by all statistics, consists of
<code>evaluate()</code> methods that take double[] arrays as arguments
- and return the value of the statistic. This interface is extended by
+ and return the value of the statistic. This interface is extended by
<a href="../apidocs/org/apache/commons/math/stat/descriptive/StorelessUnivariateStatistic.html">
StorelessUnivariateStatistic</a>, which adds <code>increment(),</code>
- <code>getResult()</code> and associated methods to support
- "storageless" implementations that maintain counters, sums or other
+ <code>getResult()</code> and associated methods to support
+ "storageless" implementations that maintain counters, sums or other
state information as values are added using the <code>increment()</code>
- method.
+ method.
</p>
<p>
- Abstract implementations of the top level interfaces are provided in
+ Abstract implementations of the top level interfaces are provided in
<a href="../apidocs/org/apache/commons/math/stat/descriptive/AbstractUnivariateStatistic.html">
AbstractUnivariateStatistic</a> and
<a href="../apidocs/org/apache/commons/math/stat/descriptive/AbstractStorelessUnivariateStatistic.html">
AbstractStorelessUnivariateStatistic</a> respectively.
</p>
<p>
- Each statistic is implemented as a separate class, in one of the
- subpackages (moment, rank, summary) and each extends one of the abstract
- classes above (depending on whether or not value storage is required to
- compute the statistic). There are several ways to instantiate and use statistics.
+ Each statistic is implemented as a separate class, in one of the
+ subpackages (moment, rank, summary) and each extends one of the abstract
+ classes above (depending on whether or not value storage is required to
+ compute the statistic). There are several ways to instantiate and use statistics.
Statistics can be instantiated and used directly, but it is generally more convenient
- (and efficient) to access them using the provided aggregates,
+ (and efficient) to access them using the provided aggregates,
<a href="../apidocs/org/apache/commons/math/stat/descriptive/DescriptiveStatistics.html">
- DescriptiveStatistics</a> and
+ DescriptiveStatistics</a> and
<a href="../apidocs/org/apache/commons/math/stat/descriptive/SummaryStatistics.html">
- SummaryStatistics.</a>
+ SummaryStatistics.</a>
</p>
<p>
- <code>DescriptiveStatistics</code> maintains the input data in memory
- and has the capability of producing "rolling" statistics computed from a
- "window" consisting of the most recently added values.
+ <code>DescriptiveStatistics</code> maintains the input data in memory
+ and has the capability of producing "rolling" statistics computed from a
+ "window" consisting of the most recently added values.
</p>
<p>
- <code>SummaryStatisics</code> does not store the input data values
- in memory, so the statistics included in this aggregate are limited to those
- that can be computed in one pass through the data without access to
- the full array of values.
+ <code>SummaryStatisics</code> does not store the input data values
+ in memory, so the statistics included in this aggregate are limited to those
+ that can be computed in one pass through the data without access to
+ the full array of values.
</p>
<p>
<table>
<tr><th>Aggregate</th><th>Statistics Included</th><th>Values stored?</th>
<th>"Rolling" capability?</th></tr><tr><td>
<a href="../apidocs/org/apache/commons/math/stat/descriptive/DescriptiveStatistics.html">
- DescriptiveStatistics</a></td><td>min, max, mean, geometric mean, n,
- sum, sum of squares, standard deviation, variance, percentiles, skewness,
+ DescriptiveStatistics</a></td><td>min, max, mean, geometric mean, n,
+ sum, sum of squares, standard deviation, variance, percentiles, skewness,
kurtosis, median</td><td>Yes</td><td>Yes</td></tr><tr><td>
<a href="../apidocs/org/apache/commons/math/stat/descriptive/SummaryStatistics.html">
- SummaryStatistics</a></td><td>min, max, mean, geometric mean, n,
+ SummaryStatistics</a></td><td>min, max, mean, geometric mean, n,
sum, sum of squares, standard deviation, variance</td><td>No</td><td>No</td></tr>
</table>
</p>
<p>
- There is also a utility class,
+ There is also a utility class,
<a href="../apidocs/org/apache/commons/math/stat/StatUtils.html">
- StatUtils</a>, that provides static methods for computing statistics
- directly from double[] arrays.
+ StatUtils</a>, that provides static methods for computing statistics
+ directly from double[] arrays.
</p>
<p>
Here are some examples showing how to compute Descriptive statistics.
<dl>
<dt>Compute summary statistics for a list of double values</dt>
<br></br>
- <dd>Using the <code>DescriptiveStatistics</code> aggregate
+ <dd>Using the <code>DescriptiveStatistics</code> aggregate
(values are stored in memory):
<source>
// Get a DescriptiveStatistics instance using factory method
-DescriptiveStatistics stats = DescriptiveStatistics.newInstance();
+DescriptiveStatistics stats = DescriptiveStatistics.newInstance();
// Add the data from the array
for( int i = 0; i < inputArray.length; i++) {
stats.addValue(inputArray[i]);
}
-// Compute some statistics
+// Compute some statistics
double mean = stats.getMean();
double std = stats.getStandardDeviation();
double median = stats.getMedian();
</source>
</dd>
- <dd>Using the <code>SummaryStatistics</code> aggregate (values are
+ <dd>Using the <code>SummaryStatistics</code> aggregate (values are
<strong>not</strong> stored in memory):
<source>
// Get a SummaryStatistics instance using factory method
-SummaryStatistics stats = SummaryStatistics.newInstance();
+SummaryStatistics stats = SummaryStatistics.newInstance();
-// Read data from an input stream,
+// Read data from an input stream,
// adding values and updating sums, counters, etc.
while (line != null) {
line = in.readLine();
@@ -157,12 +157,12 @@
}
in.close();
-// Compute the statistics
+// Compute the statistics
double mean = stats.getMean();
double std = stats.getStandardDeviation();
//double median = stats.getMedian(); <-- NOT AVAILABLE
</source>
- </dd>
+ </dd>
<dd>Using the <code>StatUtils</code> utility class:
<source>
// Compute statistics directly from the array
@@ -171,21 +171,21 @@
double std = StatUtils.variance(values);
double median = StatUtils.percentile(50);
-// Compute the mean of the first three values in the array
-mean = StatuUtils.mean(values, 0, 3);
+// Compute the mean of the first three values in the array
+mean = StatuUtils.mean(values, 0, 3);
</source>
- </dd>
- <dt>Maintain a "rolling mean" of the most recent 100 values from
+ </dd>
+ <dt>Maintain a "rolling mean" of the most recent 100 values from
an input stream</dt>
<br></br>
- <dd>Use a <code>DescriptiveStatistics</code> instance with
+ <dd>Use a <code>DescriptiveStatistics</code> instance with
window size set to 100
<source>
// Create a DescriptiveStats instance and set the window size to 100
DescriptiveStatistics stats = DescriptiveStatistics.newInstance();
stats.setWindowSize(100);
-// Read data from an input stream,
+// Read data from an input stream,
// displaying the mean of the most recent 100 observations
// after every 100 observations
long nLines = 0;
@@ -202,7 +202,7 @@
</dd>
<dt>Compute statistics in a thread-safe manner</dt>
<br/>
- <dd>Use a <code>ThreadSafeDescriptiveStatistics</code> instance
+ <dd>Use a <code>SynchronizedDescriptiveStatistics</code> instance
<source>
// Create a SynchronizedDescriptiveStatistics instance and
// use as any other DescriptiveStatistics instance
@@ -211,20 +211,20 @@
</dd>
</dl>
</p>
- </subsection>
+ </subsection>
<subsection name="1.3 Frequency distributions" href="frequency">
<p>
<a href="../apidocs/org/apache/commons/math/stat/Frequency.html">
org.apache.commons.math.stat.descriptive.Frequency</a>
provides a simple interface for maintaining counts and percentages of discrete
- values.
+ values.
</p>
- <p>
- Strings, integers, longs and chars are all supported as value types,
+ <p>
+ Strings, integers, longs and chars are all supported as value types,
as well as instances of any class that implements <code>Comparable.</code>
- The ordering of values used in computing cumulative frequencies is by
- default the <i>natural ordering,</i> but this can be overriden by supplying a
- <code>Comparator</code> to the constructor. Adding values that are not
+ The ordering of values used in computing cumulative frequencies is by
+ default the <i>natural ordering,</i> but this can be overriden by supplying a
+ <code>Comparator</code> to the constructor. Adding values that are not
comparable to those that have already been added results in an
<code>IllegalArgumentException.</code>
</p>
@@ -243,10 +243,10 @@
f.addValue(new Integer(-1));
System.out.prinltn(f.getCount(1)); // displays 3
System.out.println(f.getCumPct(0)); // displays 0.2
- System.out.println(f.getPct(new Integer(1))); // displays 0.6
+ System.out.println(f.getPct(new Integer(1))); // displays 0.6
System.out.println(f.getCumPct(-2)); // displays 0
- System.out.println(f.getCumPct(10)); // displays 1
- </source>
+ System.out.println(f.getCumPct(10)); // displays 1
+ </source>
</dd>
<dt>Count string frequencies</dt>
<br></br>
@@ -258,8 +258,8 @@
f.addValue("oNe");
f.addValue("Z");
System.out.println(f.getCount("one")); // displays 1
-System.out.println(f.getCumPct("Z")); // displays 0.5
-System.out.println(f.getCumPct("Ot")); // displays 0.25
+System.out.println(f.getCumPct("Z")); // displays 0.5
+System.out.println(f.getCumPct("Ot")); // displays 0.25
</source>
</dd>
<dd>Using case-insensitive comparator:
@@ -270,42 +270,42 @@
f.addValue("oNe");
f.addValue("Z");
System.out.println(f.getCount("one")); // displays 3
-System.out.println(f.getCumPct("z")); // displays 1
+System.out.println(f.getCumPct("z")); // displays 1
</source>
</dd>
</dl>
- </p>
+ </p>
</subsection>
<subsection name="1.4 Simple regression" href="regression">
<p>
<a href="../apidocs/org/apache/commons/math/stat/regression/SimpleRegression.html">
org.apache.commons.math.stat.regression.SimpleRegression</a>
- provides ordinary least squares regression with one independent variable,
+ provides ordinary least squares regression with one independent variable,
estimating the linear model:
</p>
<p>
<code> y = intercept + slope * x </code>
</p>
<p>
- Standard errors for <code>intercept</code> and <code>slope</code> are
+ Standard errors for <code>intercept</code> and <code>slope</code> are
available as well as ANOVA, r-square and Pearson's r statistics.
</p>
<p>
- Observations (x,y pairs) can be added to the model one at a time or they
+ Observations (x,y pairs) can be added to the model one at a time or they
can be provided in a 2-dimensional array. The observations are not stored
in memory, so there is no limit to the number of observations that can be
- added to the model.
+ added to the model.
</p>
<p>
<strong>Usage Notes</strong>: <ul>
<li> When there are fewer than two observations in the model, or when
- there is no variation in the x values (i.e. all x values are the same)
+ there is no variation in the x values (i.e. all x values are the same)
all statistics return <code>NaN</code>. At least two observations with
- different x coordinates are requred to estimate a bivariate regression
+ different x coordinates are requred to estimate a bivariate regression
model.</li>
<li> getters for the statistics always compute values based on the current
set of observations -- i.e., you can get statistics, then add more data
- and get updated statistics without using a new instance. There is no
+ and get updated statistics without using a new instance. There is no
"compute" method that updates all statistics. Each of the getters performs
the necessary computations to return the requested statistic.</li>
</ul>
@@ -313,15 +313,15 @@
<p>
<strong>Implementation Notes</strong>: <ul>
<li> As observations are added to the model, the sum of x values, y values,
- cross products (x times y), and squared deviations of x and y from their
- respective means are updated using updating formulas defined in
+ cross products (x times y), and squared deviations of x and y from their
+ respective means are updated using updating formulas defined in
"Algorithms for Computing the Sample Variance: Analysis and
- Recommendations", Chan, T.F., Golub, G.H., and LeVeque, R.J.
+ Recommendations", Chan, T.F., Golub, G.H., and LeVeque, R.J.
1983, American Statistician, vol. 37, pp. 242-247, referenced in
Weisberg, S. "Applied Linear Regression". 2nd Ed. 1985. All regression
statistics are computed from these sums.</li>
<li> Inference statistics (confidence intervals, parameter significance levels)
- are based on on the assumption that the observations included in the model are
+ are based on on the assumption that the observations included in the model are
drawn from a <a href="http://mathworld.wolfram.com/BivariateNormalDistribution.html">
Bivariate Normal Distribution</a></li>
</ul>
@@ -337,31 +337,31 @@
regression.addData(1d, 2d);
// At this point, with only one observation,
// all regression statistics will return NaN
-
+
regression.addData(3d, 3d);
-// With only two observations,
+// With only two observations,
// slope and intercept can be computed
// but inference statistics will return NaN
-
+
regression.addData(3d, 3d);
// Now all statistics are defined.
</source>
</dd>
<dd>Compute some statistics based on observations added so far
<source>
-System.out.println(regression.getIntercept());
+System.out.println(regression.getIntercept());
// displays intercept of regression line
-System.out.println(regression.getSlope());
+System.out.println(regression.getSlope());
// displays slope of regression line
-System.out.println(regression.getSlopeStdErr());
+System.out.println(regression.getSlopeStdErr());
// displays slope standard error
</source>
</dd>
<dd>Use the regression model to predict the y value for a new x value
<source>
-System.out.println(regression.predict(1.5d)
+System.out.println(regression.predict(1.5d)
// displays predicted y value for x = 1.5
</source>
More data points can be added and subsequent getXxx calls will incorporate
@@ -378,32 +378,32 @@
</dd>
<dd>Estimate regression model based on data
<source>
-System.out.println(regression.getIntercept());
+System.out.println(regression.getIntercept());
// displays intercept of regression line
-System.out.println(regression.getSlope());
+System.out.println(regression.getSlope());
// displays slope of regression line
-System.out.println(regression.getSlopeStdErr());
+System.out.println(regression.getSlopeStdErr());
// displays slope standard error
</source>
- More data points -- even another double[][] array -- can be added and subsequent
+ More data points -- even another double[][] array -- can be added and subsequent
getXxx calls will incorporate additional data in statistics.
</dd>
</dl>
</p>
</subsection>
<subsection name="1.5 Statistical tests" href="tests">
- <p>
- The interfaces and implementations in the
+ <p>
+ The interfaces and implementations in the
<a href="../apidocs/org/apache/commons/math/stat/inference/">
- org.apache.commons.math.stat.inference</a> package provide
+ org.apache.commons.math.stat.inference</a> package provide
<a href="http://www.itl.nist.gov/div898/handbook/prc/section2/prc22.htm">
- Student's t</a> and
+ Student's t</a> and
<a href="http://www.itl.nist.gov/div898/handbook/eda/section3/eda35f.htm">
- Chi-Square</a> test statistics as well as
+ Chi-Square</a> test statistics as well as
<a href="http://www.cas.lancs.ac.uk/glossary_v1.1/hyptest.html#pvalue">
- p-values</a> associated with <code>t-</code> and
+ p-values</a> associated with <code>t-</code> and
<code>Chi-Square</code> tests. The interfaces are
<a href="../apidocs/org/apache/commons/math/stat/inference/TTest.html">
TTest</a> and
@@ -420,8 +420,8 @@
TestUtils</a> class provides static methods to get test instances or
to compute test statistics directly. The examples below all use the
static methods in <code>TestUtils</code> to execute tests. To get
- test object instances, either use e.g.,
- <code>TestUtils.getTTest()</code> or use the factory directly, e.g.,
+ test object instances, either use e.g.,
+ <code>TestUtils.getTTest()</code> or use the factory directly, e.g.,
<code>TestFactory.newInstance().createChiSquareTest()</code>.
</p>
<p>
@@ -430,36 +430,36 @@
<li>Both one- and two-sample t-tests are supported. Two sample tests
can be either paired or unpaired and the unpaired two-sample tests can
be conducted under the assumption of equal subpopulation variances or
- without this assumption. When equal variances is assumed, a pooled
+ without this assumption. When equal variances is assumed, a pooled
variance estimate is used to compute the t-statistic and the degrees
of freedom used in the t-test equals the sum of the sample sizes minus 2.
- When equal variances is not assumed, the t-statistic uses both sample
- variances and the
+ When equal variances is not assumed, the t-statistic uses both sample
+ variances and the
<a href="http://www.itl.nist.gov/div898/handbook/prc/section3/gifs/nu3.gif">
- Welch-Satterwaite approximation</a> is used to compute the degrees
- of freedom. Methods to return t-statistics and p-values are provided in each
+ Welch-Satterwaite approximation</a> is used to compute the degrees
+ of freedom. Methods to return t-statistics and p-values are provided in each
case, as well as boolean-valued methods to perform fixed significance
- level tests. The names of methods or methods that assume equal
- subpopulation variances always start with "homoscedastic." Test or
+ level tests. The names of methods or methods that assume equal
+ subpopulation variances always start with "homoscedastic." Test or
test-statistic methods that just start with "t" do not assume equal
- variances. See the examples below and the API documentation for
+ variances. See the examples below and the API documentation for
more details.</li>
- <li>The validity of the p-values returned by the t-test depends on the
- assumptions of the parametric t-test procedure, as discussed
+ <li>The validity of the p-values returned by the t-test depends on the
+ assumptions of the parametric t-test procedure, as discussed
<a href="http://www.basic.nwu.edu/statguidefiles/ttest_unpaired_ass_viol.html">
here</a></li>
- <li>p-values returned by both t- and chi-square tests are exact, based
- on numerical approximations to the t- and chi-square distributions in the
+ <li>p-values returned by both t- and chi-square tests are exact, based
+ on numerical approximations to the t- and chi-square distributions in the
<code>distributions</code> package. </li>
<li>p-values returned by t-tests are for two-sided tests and the boolean-valued
methods supporting fixed significance level tests assume that the hypotheses
are two-sided. One sided tests can be performed by dividing returned p-values
(resp. critical values) by 2.</li>
<li>Degrees of freedom for chi-square tests are integral values, based on the
- number of observed or expected counts (number of observed counts - 1)
- for the goodness-of-fit tests and (number of columns -1) * (number of rows - 1)
+ number of observed or expected counts (number of observed counts - 1)
+ for the goodness-of-fit tests and (number of columns -1) * (number of rows - 1)
for independence tests.</li>
- </ul>
+ </ul>
</p>
<p>
<strong>Examples:</strong>
@@ -468,15 +468,15 @@
<br></br>
<dd>To compare the mean of a double[] array to a fixed value:
<source>
-double[] observed = {1d, 2d, 3d};
+double[] observed = {1d, 2d, 3d};
double mu = 2.5d;
-System.out.println(TestUtils.t(mu, observed);
+System.out.println(TestUtils.t(mu, observed);
</source>
The code above will display the t-statisitic associated with a one-sample
t-test comparing the mean of the <code>observed</code> values against
<code>mu.</code>
</dd>
- <dd>To compare the mean of a dataset described by a
+ <dd>To compare the mean of a dataset described by a
<a href="../apidocs/org/apache/commons/math/stat/descriptive/StatisticalSummary.html">
org.apache.commons.math.stat.descriptive.StatisticalSummary</a> to a fixed value:
<source>
@@ -487,37 +487,37 @@
for (int i = 0; i < observed.length; i++) {
sampleStats.addValue(observed[i]);
}
-System.out.println(TestUtils.t(mu, observed);
+System.out.println(TestUtils.t(mu, observed);
</source>
</dd>
<dd>To compute the p-value associated with the null hypothesis that the mean
of a set of values equals a point estimate, against the two-sided alternative that
the mean is different from the target value:
<source>
-double[] observed = {1d, 2d, 3d};
+double[] observed = {1d, 2d, 3d};
double mu = 2.5d;
System.out.println(TestUtils.tTest(mu, observed);
</source>
The snippet above will display the p-value associated with the null
- hypothesis that the mean of the population from which the
+ hypothesis that the mean of the population from which the
<code>observed</code> values are drawn equals <code>mu.</code>
</dd>
<dd>To perform the test using a fixed significance level, use:
<source>
-TestUtils.tTest(mu, observed, alpha);
+TestUtils.tTest(mu, observed, alpha);
</source>
where <code>0 < alpha < 0.5</code> is the significance level of
- the test. The boolean value returned will be <code>true</code> iff the
- null hypothesis can be rejected with confidence <code>1 - alpha</code>.
- To test, for example at the 95% level of confidence, use
+ the test. The boolean value returned will be <code>true</code> iff the
+ null hypothesis can be rejected with confidence <code>1 - alpha</code>.
+ To test, for example at the 95% level of confidence, use
<code>alpha = 0.05</code>
</dd>
<dt><strong>Two-Sample t-tests</strong></dt>
<br></br>
- <dd><strong>Example 1:</strong> Paired test evaluating
+ <dd><strong>Example 1:</strong> Paired test evaluating
the null hypothesis that the mean difference between corresponding
- (paired) elements of the <code>double[]</code> arrays
- <code>sample1</code> and <code>sample2</code> is zero.
+ (paired) elements of the <code>double[]</code> arrays
+ <code>sample1</code> and <code>sample2</code> is zero.
<p>
To compute the t-statistic:
<source>
@@ -528,21 +528,21 @@
To compute the p-value:
<source>
TestUtils.pairedTTest(sample1, sample2);
- </source>
+ </source>
</p>
<p>
To perform a fixed significance level test with alpha = .05:
<source>
-TestUtils.pairedTTest(sample1, sample2, .05);
+TestUtils.pairedTTest(sample1, sample2, .05);
</source>
</p>
The last example will return <code>true</code> iff the p-value
returned by <code>TestUtils.pairedTTest(sample1, sample2)</code>
is less than <code>.05</code>
- </dd>
+ </dd>
<dd><strong>Example 2: </strong> unpaired, two-sided, two-sample t-test using
<code>StatisticalSummary</code> instances, without assuming that
- subpopulation variances are equal.
+ subpopulation variances are equal.
<p>
First create the <code>StatisticalSummary</code> instances. Both
<code>DescriptiveStatistics</code> and <code>SummaryStatistics</code>
@@ -550,12 +550,12 @@
<code>summary2</code> are <code>SummaryStatistics</code> instances,
each of which has had at least 2 values added to the (virtual) dataset that
it describes. The sample sizes do not have to be the same -- all that is required
- is that both samples have at least 2 elements.
+ is that both samples have at least 2 elements.
</p>
<p><strong>Note:</strong> The <code>SummaryStatistics</code> class does
- not store the dataset that it describes in memory, but it does compute all
- statistics necessary to perform t-tests, so this method can be used to
- conduct t-tests with very large samples. One-sample tests can also be
+ not store the dataset that it describes in memory, but it does compute all
+ statistics necessary to perform t-tests, so this method can be used to
+ conduct t-tests with very large samples. One-sample tests can also be
performed this way.
(See <a href="#1.2 Descriptive statistics">Descriptive statistics</a> for details
on the <code>SummaryStatistics</code> class.)
@@ -563,30 +563,30 @@
<p>
To compute the t-statistic:
<source>
-TestUtils.t(summary1, summary2);
+TestUtils.t(summary1, summary2);
</source>
</p>
<p>
To compute the p-value:
<source>
TestUtils.tTest(sample1, sample2);
- </source>
+ </source>
</p>
<p>
To perform a fixed significance level test with alpha = .05:
<source>
-TestUtils.tTest(sample1, sample2, .05);
+TestUtils.tTest(sample1, sample2, .05);
</source>
- </p>
+ </p>
<p>
In each case above, the test does not assume that the subpopulation
variances are equal. To perform the tests under this assumption,
replace "t" at the beginning of the method name with "homoscedasticT"
- </p>
- </dd>
+ </p>
+ </dd>
<dt>Computing <code>chi-square</code> test statistics</dt>
<br></br>
- <dd>To compute a chi-square statistic measuring the agreement between a
+ <dd>To compute a chi-square statistic measuring the agreement between a
<code>long[]</code> array of observed counts and a <code>double[]</code>
array of expected counts, use:
<source>
@@ -594,58 +594,58 @@
double[] expected = {10.1, 9.8, 10.3};
System.out.println(TestUtils.chiSquare(expected, observed));
</source>
- the value displayed will be
+ the value displayed will be
<code>sum((expected[i] - observed[i])^2 / expected[i])</code>
</dd>
- <dd> To get the p-value associated with the null hypothesis that
+ <dd> To get the p-value associated with the null hypothesis that
<code>observed</code> conforms to <code>expected</code> use:
<source>
TestUtils.chiSquareTest(expected, observed);
- </source>
- </dd>
- <dd> To test the null hypothesis that <code>observed</code> conforms to
- <code>expected</code> with <code>alpha</code> siginficance level
+ </source>
+ </dd>
+ <dd> To test the null hypothesis that <code>observed</code> conforms to
+ <code>expected</code> with <code>alpha</code> siginficance level
(equiv. <code>100 * (1-alpha)%</code> confidence) where <code>
0 < alpha < 1 </code> use:
<source>
TestUtils.chiSquareTest(expected, observed, alpha);
- </source>
+ </source>
The boolean value returned will be <code>true</code> iff the null hypothesis
can be rejected with confidence <code>1 - alpha</code>.
</dd>
- <dd>To compute a chi-square statistic statistic associated with a
+ <dd>To compute a chi-square statistic statistic associated with a
<a href="http://www.itl.nist.gov/div898/handbook/prc/section4/prc45.htm">
chi-square test of independence</a> based on a two-dimensional (long[][])
<code>counts</code> array viewed as a two-way table, use:
<source>
TestUtils.chiSquareTest(counts);
- </source>
- The rows of the 2-way table are
+ </source>
+ The rows of the 2-way table are
<code>count[0], ... , count[count.length - 1]. </code><br></br>
- The chi-square statistic returned is
+ The chi-square statistic returned is
<code>sum((counts[i][j] - expected[i][j])^2/expected[i][j])</code>
- where the sum is taken over all table entries and
- <code>expected[i][j]</code> is the product of the row and column sums at
+ where the sum is taken over all table entries and
+ <code>expected[i][j]</code> is the product of the row and column sums at
row <code>i</code>, column <code>j</code> divided by the total count.
- </dd>
- <dd>To compute the p-value associated with the null hypothesis that
- the classifications represented by the counts in the columns of the input 2-way
+ </dd>
+ <dd>To compute the p-value associated with the null hypothesis that
+ the classifications represented by the counts in the columns of the input 2-way
table are independent of the rows, use:
<source>
TestUtils.chiSquareTest(counts);
- </source>
+ </source>
</dd>
<dd>To perform a chi-square test of independence with <code>alpha</code>
- siginficance level (equiv. <code>100 * (1-alpha)%</code> confidence)
+ siginficance level (equiv. <code>100 * (1-alpha)%</code> confidence)
where <code>0 < alpha < 1 </code> use:
<source>
TestUtils.chiSquareTest(counts, alpha);
- </source>
- The boolean value returned will be <code>true</code> iff the null
+ </source>
+ The boolean value returned will be <code>true</code> iff the null
hypothesis can be rejected with confidence <code>1 - alpha</code>.
</dd>
</dl>
- </p>
+ </p>
</subsection>
</section>
</body>