Package org.jquantlib.math.distributions

Examples of org.jquantlib.math.distributions.InverseCumulativeNormal

81
82
83
84
85
86
87
88
     * \exp (-u^2/2) du \f]
     */
    public double gaussianPercentile(final double percentile) {
        QL.require(percentile > 0.0 , "percentile must be > 0.0"); // QA:[RG]::verified // TODO: message
        QL.require(percentile < 1.0 , "percentile must be < 1.0"); // QA:[RG]::verified // TODO: message
        final InverseCumulativeNormal gInverse = new InverseCumulativeNormal(statistics.mean(), statistics.standardDeviation());
        return gInverse.op(percentile);
    }
View Full Code Here
126
127
128
129
130
131
132
133
134
135
136
137
    public double gaussianExpectedShortfall(final double percentile) {
        if (percentile >= 1.0 || percentile < 0.9)
            throw new IllegalArgumentException("percentile (" + percentile + ") out of range [0.9, 1)");
        final double m = statistics.mean();
        final double std = statistics.standardDeviation();
        final InverseCumulativeNormal gInverse = new InverseCumulativeNormal(m, std);
        final double var = gInverse.op(1.0 - percentile);
        final NormalDistribution g = new NormalDistribution(m, std);
        final double result = m - std * std * g.op(var) / (1.0 - percentile);
        // expectedShortfall must be a loss
        // this means that it has to be MIN(result, 0.0)
        // expectedShortfall must also be a positive quantity, so -MIN(*)
 
View Full Code Here
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
        //FIXME: obtain original value :: this is a thread safety problem :(
        final boolean oldHighPrecision = settings.isRefineHighPrecisionUsingHalleysMethod();

        settings.setRefineHighPrecisionUsingHalleysMethod(false);
        InverseCumulativeNormal icn;

        //test the normal values
        icn = new InverseCumulativeNormal();
        for (final double[] normalTestvalue : normal_testvalues) {
            final double x_position = normalTestvalue[0];
            final double tolerance = 1.0e-15;//(Math.abs(x_position)<3.01) ? 1.0e-15: 1.0e-10;

            final double normal_expected = normalTestvalue[1];
            final double computed_normal = icn.op(x_position);
            if (Math.abs(normal_expected-computed_normal)>tolerance) {
                fail("x_position " + x_position + " normal_expected: " + normal_expected + " normal_computed: " + normal_expected);
            }
        }


        //test the normal values using high machine precision Halley's method
        settings.setRefineHighPrecisionUsingHalleysMethod(true);
        icn = new InverseCumulativeNormal();
        for (final double[] precisionTestvalue : precision_testvalues) {
            final double x_position = precisionTestvalue[0];
            final double tolerance = 1.0e-15;//(Math.abs(x_position)<3.01) ? 1.0e-15: 1.0e-10;

            final double precision_expected = precisionTestvalue[1];
            final double computed_precision = icn.op(x_position);

            if (Math.abs(precision_expected-computed_precision)>tolerance) {
                fail("x_position " + x_position + " precision_expected: " + precision_expected + " precision_computed: " + computed_precision);
            }
        }
View Full Code Here
76
77
78
79
80
81
82
83
          public static double evaluateGammaDistribution(double a, double x) {
              GammaDistribution gd = new GammaDistribution(a);
              return gd.op(x);
          }
           public static double evaluateInverseCumulativeNormal(double average, double sigma, double x){
               InverseCumulativeNormal icn = new InverseCumulativeNormal(average,sigma);
               return icn.op(x);
           }
View Full Code Here
121
122
123
124
125
126
127
128
   
    public /*@Real*/ double gaussianPercentile(/*@Real*/ double percentile) /* @ReadOnly */ {
    QL.require(percentile>0.0, "percentile must be > 0.0");
    QL.require(percentile<1.0, "percentile must be < 1.0");
    final InverseCumulativeNormal gInverse = new InverseCumulativeNormal(mean(), standardDeviation());
    return gInverse.op(percentile);
  }
View Full Code Here
175
176
177
178
179
180
181
182
183
184
185
186
     */
    public /*@Real*/ double gaussianExpectedShortfall(/*@Real*/ double percentile) /* @ReadOnly */ {
        QL.require(percentile<1.0 && percentile>=0.9, "percentile is out of range [0.9, 1)");
        /*@Real*/ double m = this.mean();
        /*@Real*/ double std = this.standardDeviation();
        final InverseCumulativeNormal gInverse = new InverseCumulativeNormal(m, std);
        /*@Real*/ double var = gInverse.op(1.0-percentile);
        final NormalDistribution g = new NormalDistribution(m, std);
        /*@Real*/ double result = m - std*std*g.op(var)/(1.0-percentile);
        // expectedShortfall must be a loss: this means that it has to be MIN(result, 0.0)
        // expectedShortfall must also be a positive quantity, so -MIN(*)
        return -Math.min(result, 0.0);
View Full Code Here
TOP

Related Classes of org.jquantlib.math.distributions.InverseCumulativeNormal

  • org.jquantlib.math.statistics.GaussianStatistics
  • org.jquantlib.math.statistics.GenericGaussianStatistics
  • org.jquantlib.ooimpl.MathHelper
  • org.jquantlib.Settings
  • org.jquantlib.testsuite.math.distributions.InverseCumulativeNormalTest
  • org.jquantlib.lang.exceptions.LibraryException
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.