aherbert commented on issue #8: Addition of Log Cauchy Distribution
URL: https://github.com/apache/commons-statistics/pull/8#issuecomment-493971154
 
 
   Looking at the sister CauchyDistribution you should be able to define the 
method:
   
   ```
   /**
    * {@inheritDoc}
    *
    * Returns {@code 0} when {@code p == 0}
    * and {@code Double.POSITIVE_INFINITY} when {@code p == 1}.
    */
   @Override
   public double inverseCumulativeProbability(double p) {
       double ret;
       if (p < 0 ||
           p > 1) {
           throw new DistributionException(DistributionException.OUT_OF_RANGE, 
p, 0, 1);
       } else if (p == 0) {
           ret = 0;
       } else  if (p == 1) {
           ret = Double.POSITIVE_INFINITY;
       } else {
           ret = Math.exp(location + scale * Math.tan(Math.PI * (p - .5)));
       }
       return ret;
   }
   ```
   
   Also this may be a worthwhile optimisation:
   
   ```
   /** {@inheritDoc} */
   @Override
   public double logDensity(double x) {
       if (x <= 0) {
           return Double.NEGATIVE_INFINITY;
       }
       final double logX = Math.log(x);
       final double dev = logX - location;
       return Math.log((1 / Math.PI) * (scale / (dev * dev + scale * scale))) - 
logX;
   }
   ```
   
   It is the the same as `Math.log(density(x))` but should be investigated to 
see if it expands the range of x that can be computed.
   

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
[email protected]


With regards,
Apache Git Services

Reply via email to