Rank and Percentile


Rank and percentile conversion of sample data

Sample data may often be converted so that it is represented in an alternative format, without actually altering the relationship of one data element to the others. This modified data can then be used for specific further analysis.

Data is usually ranked, or arranged in order so that rank '1' is assigned to either the lowest or highest data element and subsequent rankings are assigned to the other data elements on the basis of magnitude. The ranking of data often forms the basis of many non-parametric hypothesis tests. Data converted to ranks using this tool may also be used for non-parametric hypothesis tests of a specialised nature which are beyond the scope of this package contents.

When summarizing or describing the properties of sample data the data itself may be represented by measures of non-central location known as quantiles. Typical measures of central location include the median and mean. Typical quantile measures include quartiles and percentiles. For example, the median splits ordered sample data in half, quartiles split it into four equal portions and percentiles split it into hundredths.

Measures of non-central location have limited applications but may be used to locate the position of single data elements and their relationship to others (eg. finding the position of a student's score among a large data set of examination scores, etc.).

Script operation

This tool operates in much the same way as most of the others with no specific departures from the usual methods needed.

Click here for information about general script usage.

Typical input data and script output are shown in the example below. Note that any column titles or labels may be included in the output data by being included in the input range. This tool will accept single or multiple columns of sample data.

 Raw data:

 Sample1   Sample2
      60	75
      65	89
      90	93
      45	66
      66	78
      66	84
      89	97
      92       100
      75	75


 Spreadsheet output:

 Sample1  Rank  Percentile  Percentile  Sample2  Rank  Percentile  Percentile
		Rank        Point       	       Rank        Point

      45     9  	 6         0.0       66     9   	6         0.0
      60     8  	17        12.5       75     7          22        12.5
      65     7  	28        25.0       75     7          22        12.5
      66     5  	44        37.5       78     6          39        37.5
      66     5  	44        37.5       84     5          50        50.0
      75     4  	61        62.5       89     4          61        62.5
      89     3  	72        75.0       93     3          72        75.0
      90     2  	83        87.5       97     2          83        87.5
      92     1  	94       100.0      100     1          94       100.0


Back to Main Document