Page 91 - DECO504_STATISTICAL_METHODS_IN_ECONOMICS_ENGLISH
P. 91

Unit 6: Dispersion: Meaning and Characteristics, Absolute and Relative Measures of Dispersion including Range...


            Definition                                                                               Notes

            There is no standard definition of percentile, however all definitions yield similar results when the
            number of observations is very large.
            Nearest rank

            One definition of percentile, often given in texts, is that the P-th percentile (  < P  100  of N ordered
                                                                               ) ≤ 0
            values (arranged from least to greatest) is obtained by first calculating the (ordinal) rank

                                           P      1
                                      n =    ×  +N
                                          100     2
            rounding the result to the nearest integer, and then taking the value that corresponds to that rank.

                                                                      P
            (Note that the rounded value of n is just the least integer which exceeds   × N .)
                                                                      100
            For example, by this definition, given the numbers
                          15, 20, 35, 40, 50
                         th
            the rank of the 30  percentile would be
                                          30     1
                                              5
                                      n =    ×+    = 2.
                                          100    2
                     th
            Thus the 30  percentile is the second number in the sorted list, 20.
            The 35  percentile would have rank
                 th
                                          35     1
                                              5
                                      n =    ×+    = 2.25,
                                          100    2
            so the 35  percentile would be the second number again (since 2.25 rounds down to 2) or 20
                  th
            The 40  percentile would have rank
                 th
                                          40     1
                                              5
                                      n =    ×+    = 2.5,
                                          100    2
            so the 40  percentile would be the third number (since 2.5 rounds up to 3), or 35.
                  th
                  th
            The 100  percentile is defined to be the largest value. (In this case we do not use the above definition
            with P = 100, because the rank n would be greater than the number N of values in the original list.)
            In lists with fewer than 100 values the same number can occupy more than one percentile group.
            Linear interpolation between closest ranks
            An alternative to rounding used in many applications is to use linear interpolation between the two
            nearest ranks.
            In particular, given the N sorted values v 1  ≤  2  ≤ v  3  ≤ v   ... ≤ v , we define the percent rank corresponding
                                                         N
            to the n  value as:
                  th
                                             ⎛ 100  1  ⎞
                                      p =    ⎜  n  −  ⎟  .
                                       n   N  ⎝  2  ⎠
                                      th
            In this way, for example, if N = 5  percent rank corresponding to the third value is
                                             ⎛ 100  1 ⎞
                                      p =    ⎜  3 −  ⎟   = 50.
                                       3   5  ⎝  2  ⎠





                                             LOVELY PROFESSIONAL UNIVERSITY                                       85
   86   87   88   89   90   91   92   93   94   95   96