让我们创建一个名为numbers的示例表

这个答案是针对mysql数据库的

在postgres Sql中，它简单地使用per_cont函数

创建表数字( num INT, 频率整数 ）;

在数字表中插入值

插入数字 (7) 0 (1, 1), (2、3), (1) 3 (9,1), (1, 1), (2、3), (1) 3 (9,1);

——select * from numbers

作为递归num_frequency (num,frequency, i) （ 选择num,频率,1 从数字 UNION ALL 选择num,频率,i + 1 从num_frequency num_frequency的地方。I < num_frequency.frequency ）

select * (max(当numbers=lower_limit时，则num else null end)/2 +max(当数字=upper_limit时，则num else null end)/2)作为中位数 从( select *, total_number % 2, 情况下 当total_number%2=0时，total_number/2 Else (total_number+1)/2 end as lower_limit， 情况下 当total_number%2=0时，total_number/2+1 其他(total_number + 1) / 2 结束为upper_limit

从( Select *，max(numbers) over() as total_number from ( Select num,row_number() over(按num排序) 作为num_frequency中的数字 b) b) b)

你可以使用这里的用户定义函数。

我使用下表的解决方案在MySQL:

CREATE TABLE transactions (
  transaction_id int , user_id int , merchant_name varchar(255), transaction_date date , amount int
);

INSERT INTO transactions (transaction_id, user_id, merchant_name, transaction_date, amount)  
VALUES (1, 1 ,'abc', '2015-08-17', 100),(2, 2, 'ced', '2015-2-17', 100),(3, 1, 'def', '2015-2-16', 121),
(4, 1 ,'ced', '2015-3-17', 110),(5, 1, 'ced', '2015-3-17', 150),(6, 2 ,'abc', '2015-4-17', 130), 
(7, 3 ,'ced', '2015-12-17', 10),(8, 3 ,'abc', '2015-8-17', 100),(9, 2 ,'abc', '2015-12-17', 140),(10, 1,'abc', '2015-9-17', 100),
(11, 1 ,'abc', '2015-08-17', 121),(12, 2 ,'ced', '2015-12-23', 130),(13, 1 ,'def', '2015-12-23', 13),(3, 4, 'abc', '2015-2-16', 120),(3, 4, 'def', '2015-2-16', 121),(3, 4, 'ced', '2015-2-16', 121);

计算“金额”列的中位数:

WITH Numbered AS 
(
SELECT *, COUNT(*) OVER () AS TotatRecords,
    ROW_NUMBER() OVER (ORDER BY amount) AS RowNum
FROM transactions
)
SELECT Avg(amount)
FROM Numbered
WHERE RowNum IN ( FLOOR((TotatRecords+1)/2), FLOOR((TotatRecords+2)/2) )
;

TotalRecords = 16 and Median = 120.5000

此查询将适用于两种情况，即偶数和奇数记录。

上面的大多数解决方案只适用于表中的一个字段，您可能需要获得查询中多个字段的中位数(第50百分位数)。

我用这个:

SELECT CAST(SUBSTRING_INDEX(SUBSTRING_INDEX(
 GROUP_CONCAT(field_name ORDER BY field_name SEPARATOR ','),
  ',', 50/100 * COUNT(*) + 1), ',', -1) AS DECIMAL) AS `Median`
FROM table_name;

你可以将上面例子中的“50”替换为任何百分位数，这是非常有效的。

只要确保你有足够的内存给GROUP_CONCAT，你可以改变它:

SET group_concat_max_len = 10485760; #10MB max length

详情:http://web.performancerasta.com/metrics-tips-calculating-95th-99th-or-any-percentile-with-single-mysql-query/

MySQL文档中这一页的注释有以下建议:

-- (mostly) High Performance scaling MEDIAN function per group
-- Median defined in http://en.wikipedia.org/wiki/Median
--
-- by Peter Hlavac
-- 06.11.2008
--
-- Example Table:

DROP table if exists table_median;
CREATE TABLE table_median (id INTEGER(11),val INTEGER(11));
COMMIT;


INSERT INTO table_median (id, val) VALUES
(1, 7), (1, 4), (1, 5), (1, 1), (1, 8), (1, 3), (1, 6),
(2, 4),
(3, 5), (3, 2),
(4, 5), (4, 12), (4, 1), (4, 7);



-- Calculating the MEDIAN
SELECT @a := 0;
SELECT
id,
AVG(val) AS MEDIAN
FROM (
SELECT
id,
val
FROM (
SELECT
-- Create an index n for every id
@a := (@a + 1) mod o.c AS shifted_n,
IF(@a mod o.c=0, o.c, @a) AS n,
o.id,
o.val,
-- the number of elements for every id
o.c
FROM (
SELECT
t_o.id,
val,
c
FROM
table_median t_o INNER JOIN
(SELECT
id,
COUNT(1) AS c
FROM
table_median
GROUP BY
id
) t2
ON (t2.id = t_o.id)
ORDER BY
t_o.id,val
) o
) a
WHERE
IF(
-- if there is an even number of elements
-- take the lower and the upper median
-- and use AVG(lower,upper)
c MOD 2 = 0,
n = c DIV 2 OR n = (c DIV 2)+1,

-- if its an odd number of elements
-- take the first if its only one element
-- or take the one in the middle
IF(
c = 1,
n = 1,
n = c DIV 2 + 1
)
)
) a
GROUP BY
id;

-- Explanation:
-- The Statement creates a helper table like
--
-- n id val count
-- ----------------
-- 1, 1, 1, 7
-- 2, 1, 3, 7
-- 3, 1, 4, 7
-- 4, 1, 5, 7
-- 5, 1, 6, 7
-- 6, 1, 7, 7
-- 7, 1, 8, 7
--
-- 1, 2, 4, 1

-- 1, 3, 2, 2
-- 2, 3, 5, 2
--
-- 1, 4, 1, 4
-- 2, 4, 5, 4
-- 3, 4, 7, 4
-- 4, 4, 12, 4


-- from there we can select the n-th element on the position: count div 2 + 1 

我没有将这个解决方案的性能与这里发布的其他答案进行比较，但我发现这个解决方案是最容易理解的，并且涵盖了计算中位数的全部数学公式。换句话说，这个解决方案对于偶数和奇数数据集足够健壮:

SELECT CASE 
-- odd-numbered data sets:
WHEN MOD(COUNT(*), 2) = 1 THEN (SELECT median.<value> AS median
FROM
(SELECT t1.<value>
  FROM (SELECT <value>, 
               ROW_NUMBER() OVER(ORDER BY <value>) AS rownum
          FROM <data>) t1,
       (SELECT COUNT(*) AS num_records FROM <data>) t2
 WHERE t1.rownum =(t2.num_records) / 2) as median)
-- even-numbered data sets:
ELSE (select (low_bound.<value> + up_bound.<value>) / 2 AS median
FROM
(SELECT t1.<value>
  FROM (SELECT <value>, 
               ROW_NUMBER() OVER(ORDER BY <value>) AS rownum
          FROM <data>) t1,
       (SELECT COUNT(*) AS num_records FROM <data>) t2
 WHERE t1.rownum =(t2.num_records - 1) / 2) as low_bound,
 (SELECT t1.<value>
  FROM (SELECT <value>, 
               ROW_NUMBER() OVER(ORDER BY <value>) AS rownum
          FROM station) t1,
       (SELECT COUNT(*) AS num_records FROM data) t2
 WHERE t1.rownum =(t2.num_records + 1) / 2) as up_bound)
END
FROM <data>