Are there any Linear Regression Function in SQL Server?

I've actually written an SQL routine using Gram-Schmidt orthoganalization. It, as well as other machine learning and forecasting routines, is available at sqldatamine.blogspot.com

At the suggestion of Brad Larson I've added the code here rather than just direct users to my blog. This produces the same results as the linest function in Excel. My primary source is Elements of Statistical Learning (2008) by Hastie, Tibshirni and Friedman.

--Create a table of data
create table #rawdata (id int,area float, rooms float, odd float,  price float)

insert into #rawdata select 1, 2201,3,1,400
insert into #rawdata select 2, 1600,3,0,330
insert into #rawdata select 3, 2400,3,1,369
insert into #rawdata select 4, 1416,2,1,232
insert into #rawdata select 5, 3000,4,0,540

--Insert the data into x & y vectors
select id xid, 0 xn,1 xv into #x from #rawdata
union all
select id, 1,rooms  from #rawdata
union all
select id, 2,area  from #rawdata
union all
select id, 3,odd  from #rawdata

select id yid, 0 yn, price yv  into #y from #rawdata

--create a residuals table and insert the intercept (1)
create table #z (zid int, zn int, zv float)
insert into #z select id , 0 zn,1 zv from #rawdata

--create a table for the orthoganal (#c) & regression(#b) parameters
create table #c(cxn int, czn int, cv float) 
create table #b(bn int, bv float) 


--@p is the number of independent variables including the intercept (@p = 0)
declare @p int
set @p = 1


--Loop through each independent variable and estimate the orthagonal parameter (#c)
-- then estimate the residuals and insert into the residuals table (#z)
while @p <= (select max(xn) from #x)
begin   
        insert into #c
    select  xn cxn,  zn czn, sum(xv*zv)/sum(zv*zv) cv 
        from #x join  #z on  xid = zid where zn = @p-1 and xn>zn group by xn, zn

    insert into #z
    select zid, xn,xv- sum(cv*zv) 
        from #x join #z on xid = zid   join  #c  on  czn = zn and cxn = xn  where xn = @p and zn<xn  group by zid, xn,xv

    set @p = @p +1
end

--Loop through each independent variable and estimate the regression parameter by regressing the orthoganal
-- resiuduals on the dependent variable y
while @p>=0 
begin

    insert into #b
    select zn, sum(yv*zv)/ sum(zv*zv) 
        from #z  join 
            (select yid, yv-isnull(sum(bv*xv),0) yv from #x join #y on xid = yid left join #b on  xn=bn group by yid, yv) y
        on zid = yid where zn = @p  group by zn

    set @p = @p-1
end

--The regression parameters
select * from #b

--Actual vs. fit with error
select yid, yv, fit, yv-fit err from #y join 
    (select xid, sum(xv*bv) fit from #x join #b on xn = bn  group by xid) f
     on yid = xid

--R Squared
select 1-sum(power(err,2))/sum(power(yv,2)) from 
(select yid, yv, fit, yv-fit err from #y join 
    (select xid, sum(xv*bv) fit from #x join #b on xn = bn  group by xid) f
     on yid = xid) d

This is an alternate method, based off a blog post on Linear Regression in T-SQL, which uses the following equations:

enter image description here

The SQL suggestion in the blog uses cursors though. Here's a prettified version of a forum answer that I used:

table
-----
X (numeric)
Y (numeric)

/**
 * m = (nSxy - SxSy) / (nSxx - SxSx)
 * b = Ay - (Ax * m)
 * N.B. S = Sum, A = Mean
 */
DECLARE @n INT
SELECT @n = COUNT(*) FROM table
SELECT (@n * SUM(X*Y) - SUM(X) * SUM(Y)) / (@n * SUM(X*X) - SUM(X) * SUM(X)) AS M,
       AVG(Y) - AVG(X) *
       (@n * SUM(X*Y) - SUM(X) * SUM(Y)) / (@n * SUM(X*X) - SUM(X) * SUM(X)) AS B
FROM table

To the best of my knowledge, there is none. Writing one is pretty straightforward, though. The following gives you the constant alpha and slope beta for y = Alpha + Beta * x + epsilon:

-- test data (GroupIDs 1, 2 normal regressions, 3, 4 = no variance)
WITH some_table(GroupID, x, y) AS
(       SELECT 1,  1,  1    UNION SELECT 1,  2,  2    UNION SELECT 1,  3,  1.3  
  UNION SELECT 1,  4,  3.75 UNION SELECT 1,  5,  2.25 UNION SELECT 2, 95, 85    
  UNION SELECT 2, 85, 95    UNION SELECT 2, 80, 70    UNION SELECT 2, 70, 65    
  UNION SELECT 2, 60, 70    UNION SELECT 3,  1,  2    UNION SELECT 3,  1, 3
  UNION SELECT 4,  1,  2    UNION SELECT 4,  2,  2),
 -- linear regression query
/*WITH*/ mean_estimates AS
(   SELECT GroupID
          ,AVG(x * 1.)                                             AS xmean
          ,AVG(y * 1.)                                             AS ymean
    FROM some_table
    GROUP BY GroupID
),
stdev_estimates AS
(   SELECT pd.GroupID
          -- T-SQL STDEV() implementation is not numerically stable
          ,CASE      SUM(SQUARE(x - xmean)) WHEN 0 THEN 1 
           ELSE SQRT(SUM(SQUARE(x - xmean)) / (COUNT(*) - 1)) END AS xstdev
          ,     SQRT(SUM(SQUARE(y - ymean)) / (COUNT(*) - 1))     AS ystdev
    FROM some_table pd
    INNER JOIN mean_estimates  pm ON pm.GroupID = pd.GroupID
    GROUP BY pd.GroupID, pm.xmean, pm.ymean
),
standardized_data AS                   -- increases numerical stability
(   SELECT pd.GroupID
          ,(x - xmean) / xstdev                                    AS xstd
          ,CASE ystdev WHEN 0 THEN 0 ELSE (y - ymean) / ystdev END AS ystd
    FROM some_table pd
    INNER JOIN stdev_estimates ps ON ps.GroupID = pd.GroupID
    INNER JOIN mean_estimates  pm ON pm.GroupID = pd.GroupID
),
standardized_beta_estimates AS
(   SELECT GroupID
          ,CASE WHEN SUM(xstd * xstd) = 0 THEN 0
                ELSE SUM(xstd * ystd) / (COUNT(*) - 1) END         AS betastd
    FROM standardized_data pd
    GROUP BY GroupID
)
SELECT pb.GroupID
      ,ymean - xmean * betastd * ystdev / xstdev                   AS Alpha
      ,betastd * ystdev / xstdev                                   AS Beta
FROM standardized_beta_estimates pb
INNER JOIN stdev_estimates ps ON ps.GroupID = pb.GroupID
INNER JOIN mean_estimates  pm ON pm.GroupID = pb.GroupID

Here GroupID is used to show how to group by some value in your source data table. If you just want the statistics across all data in the table (not specific sub-groups), you can drop it and the joins. I have used the WITH statement for sake of clarity. As an alternative, you can use sub-queries instead. Please be mindful of the precision of the data type used in your tables as the numerical stability can deteriorate quickly if the precision is not high enough relative to your data.

EDIT: (in answer to Peter's question for additional statistics like R2 in the comments)

You can easily calculate additional statistics using the same technique. Here is a version with R2, correlation, and sample covariance:

-- test data (GroupIDs 1, 2 normal regressions, 3, 4 = no variance)
WITH some_table(GroupID, x, y) AS
(       SELECT 1,  1,  1    UNION SELECT 1,  2,  2    UNION SELECT 1,  3,  1.3  
  UNION SELECT 1,  4,  3.75 UNION SELECT 1,  5,  2.25 UNION SELECT 2, 95, 85    
  UNION SELECT 2, 85, 95    UNION SELECT 2, 80, 70    UNION SELECT 2, 70, 65    
  UNION SELECT 2, 60, 70    UNION SELECT 3,  1,  2    UNION SELECT 3,  1, 3
  UNION SELECT 4,  1,  2    UNION SELECT 4,  2,  2),
 -- linear regression query
/*WITH*/ mean_estimates AS
(   SELECT GroupID
          ,AVG(x * 1.)                                             AS xmean
          ,AVG(y * 1.)                                             AS ymean
    FROM some_table pd
    GROUP BY GroupID
),
stdev_estimates AS
(   SELECT pd.GroupID
          -- T-SQL STDEV() implementation is not numerically stable
          ,CASE      SUM(SQUARE(x - xmean)) WHEN 0 THEN 1 
           ELSE SQRT(SUM(SQUARE(x - xmean)) / (COUNT(*) - 1)) END AS xstdev
          ,     SQRT(SUM(SQUARE(y - ymean)) / (COUNT(*) - 1))     AS ystdev
    FROM some_table pd
    INNER JOIN mean_estimates  pm ON pm.GroupID = pd.GroupID
    GROUP BY pd.GroupID, pm.xmean, pm.ymean
),
standardized_data AS                   -- increases numerical stability
(   SELECT pd.GroupID
          ,(x - xmean) / xstdev                                    AS xstd
          ,CASE ystdev WHEN 0 THEN 0 ELSE (y - ymean) / ystdev END AS ystd
    FROM some_table pd
    INNER JOIN stdev_estimates ps ON ps.GroupID = pd.GroupID
    INNER JOIN mean_estimates  pm ON pm.GroupID = pd.GroupID
),
standardized_beta_estimates AS
(   SELECT GroupID
          ,CASE WHEN SUM(xstd * xstd) = 0 THEN 0
                ELSE SUM(xstd * ystd) / (COUNT(*) - 1) END         AS betastd
    FROM standardized_data
    GROUP BY GroupID
)
SELECT pb.GroupID
      ,ymean - xmean * betastd * ystdev / xstdev                   AS Alpha
      ,betastd * ystdev / xstdev                                   AS Beta
      ,CASE ystdev WHEN 0 THEN 1 ELSE betastd * betastd END        AS R2
      ,betastd                                                     AS Correl
      ,betastd * xstdev * ystdev                                   AS Covar
FROM standardized_beta_estimates pb
INNER JOIN stdev_estimates ps ON ps.GroupID = pb.GroupID
INNER JOIN mean_estimates  pm ON pm.GroupID = pb.GroupID

EDIT 2 improves numerical stability by standardizing data (instead of only centering) and by replacing STDEV because of numerical stability issues. To me, the current implementation seems to be the best trade-off between stability and complexity. I could improve stability by replacing my standard deviation with a numerically stable online algorithm, but this would complicate the implementation substantantially (and slow it down). Similarly, implementations using e.g. Kahan(-Babuška-Neumaier) compensations for the SUM and AVG seem to perform modestly better in limited tests, but make the query much more complex. And as long as I do not know how T-SQL implements SUM and AVG (e.g. it might already be using pairwise summation), I cannot guarantee that such modifications always improve accuracy.