Changeset 168

Timestamp:

Sep 23, 2004, 3:27:03 PM (19 years ago)

Author:

Peter

Message:

percentile modified (is now defined as in GSL)

Location:

trunk/src

Files:

• Statistics.cc (modified) (2 diffs)
• Statistics.h (modified) (1 diff)

trunk/src/Statistics.cc

@@ -8 +8 @@
 #include <algorithm>
 
+#include <cmath>
 #include <cstdlib>
 #include <iostream>
@@ -32 +33 @@
   double Statistics::percentile(std::vector<double>& vec, double percentile) 
   {
-    sort(vec.begin(), vec.end());
-    double j = percentile/100 * vec.size();
     if (percentile==100)
-      return vec[vec.size()-1];   
-    
-    double k = j + 0.5 - static_cast<int> (j+0.5);
-    if (k<.500000000001 && k>.499999999999){
-      int i = static_cast<int>(j+0.5);
-      return (vec[i]+vec[i-1])/2;
+      return  vec[vec.size()-1];
+    else{
+      sort(vec.begin(), vec.end());
+      double j = percentile/100 * (vec.size()-1);
+      int i = static_cast<int>(j);
+      return (1-j+floor(j))*vec[i] + (j-floor(j))*vec[i+1];
     }
-    else{
-      int i = static_cast<int>(j);
-      return  vec[i];
-    }
-    
   }
 
   double Statistics::percentile(std::vector<size_t>& vec, double percentile) 
   {
-    sort(vec.begin(), vec.end());
-    double j = percentile/100 * vec.size();
     if (percentile==100)
-      return vec[vec.size()-1];   
-    
-    double k = j + 0.5 - static_cast<int> (j+0.5);
-    if (k<.500000000001 && k>.499999999999){
-      int i = static_cast<int>(j+0.5);
-      double r = static_cast<double>(vec[i]+vec[i-1])/2;
-      return r;
-      
-    }
+      return vec[vec.size()-1];
     else{
+      sort(vec.begin(), vec.end());
+      double j = percentile/100 * (vec.size()-1);
       int i = static_cast<int>(j);
-      return  static_cast<double>(vec[i]);
+      return (1-j+floor(j))*vec[i] + (j-floor(j))*vec[i+1];
     }
     

trunk/src/Statistics.h

@@ -27 +27 @@
 
     ///
-    /// @return median
+    /// Median is defined to be value in the middle. If number of
+    /// values is even median is the average of the two middle
+    /// values. @return median
     ///
     double median(std::vector<double>&);  
 
     ///
-    /// @return median
+    /// Median is defined to be value in the middle. If number of
+    /// values is even median is the average of the two middle
+    /// values. @return median
     ///
     double median(std::vector<size_t>&);  
 
     ///
-    /// @return \a i'th percentile
+    /// The percentile is determined by the \a p, a number between 0
+    /// and 100. The percentile is found by interpolation, using the
+    /// formula \f$ percentile = (1 - \delta) x_i + \delta x_{i+1} \f$
+    /// where \a p is floor\f$((n - 1)p/100)\f$ and \f$ \delta \f$ is
+    /// \f$ (n-1)p/100 - i \f$.Thus the minimum value of the vector is
+    /// given by p equal to zero, the maximum is given by p equal to
+    /// 100 and the median value is given by p equal to 50. Since the
+    /// algorithm for computing percentiles involves interpolation
+    /// this function always returns a floating-point number, even for
+    /// integer data types.  @return \a i'th percentile
     ///
-    double percentile(std::vector<double>&, double i);
+    double percentile(std::vector<double>&, double p);
 
     ///
-    /// @return \a i'th percentile
+    /// The percentile is determined by the \a p, a number between 0
+    /// and 100. The percentile is found by interpolation, using the
+    /// formula \f$ percentile = (1 - \delta) x_i + \delta x_{i+1} \f$
+    /// where \a p is floor\f$((n - 1)p/100)\f$ and \f$ \delta \f$ is
+    /// \f$ (n-1)p/100 - i \f$.Thus the minimum value of the vector is
+    /// given by p equal to zero, the maximum is given by p equal to
+    /// 100 and the median value is given by p equal to 50. Since the
+    /// algorithm for computing percentiles involves interpolation
+    /// this function always returns a floating-point number, even for
+    /// integer data types.  @return \a i'th percentile
     ///
     double percentile(std::vector<size_t>&, double i);