I believe we are doing the data analysis, statistical knowledge to use when needed, you should encounter the first p percentile
So here I am going to talk about my personal understanding:
find related concepts from Wikipedia:
Percentile, statistical terms, if a set of data from small to large, and calculate the cumulative percentile, the percentile by a percentage of the value of the data is called the corresponding percentile the number of bits to represent the k-th percentile Pk.
Pk represents at least k% or less of the number of data, while also (100-k)% of the data is greater than or equal to this number.
Ql = P25
P50 Q2 =
P75 = Q3
P50 called median
difference between P75 and P25 is referred interquartile
See the above description, it is probably a little knowledge, but just focus on the core sentence: Pk indicates that at least k% of the data is equal to or less than this number, while there (100-k)% of the data is greater than or equal to this number.
I believe almost all understand, that is, look at all of the sorted (Small -> Large) The number of positions, so we look at the Dharma:
Seeking:
if the number of group information N, and in ascending order, set N × k% = a
- a is an integer then a fetch of a + 1, and an average value thereof
- The next integer a is not an integer taking a close (a = 1.2 takes 2)
Then we look at the example it
is assumed that data is:
chestnuts 1
1,2，3,4，5,6，7,8，9,10
total: 10
then the p (25) is much percentile: 3 ----------------- of> 10 25% = 2.5 At the third number is 3
the p (50) What is percentile: 5.5 ---------------------- of> 10 50% = 5 and an integer of 5 to take the first of the 5 + 1 the average value
of p (75) is much percentile: 8 -----------------------> = 75% * 10 7.5 8 taken number
Chestnuts 2
6,7,15,36,39,40,41,42,43,47,49
Then the first p (25) percentile is the number: 15
first p (50) percentile is the number: 40
first p (75) percentile is the number: 43
Chestnuts 3
7,15,36,39,40,41
Then the first p (25) percentile is the number: 15
first p (50) percentile is the number: 37.5
on p (75) percentile is the number: 40
Chestnuts 4
1,2,3,4
Then the first p (25) percentile is the number: 1.5
on p (50) percentile is the number: 2.5
on p (75) percentile is the number: 3.5
Believe that here we all understand almost, if not quite understand, at least this is the percentile will forget it
can also be seen from a few chestnuts, 50th percentile median is obvious, so sometimes we when calculation of the median can be used to calculate p-percentile.
