Are there any Linear Regression Function in SQL Server?

Question

Are there any Linear Regression Function in SQL Server 2005/2008, similar to the the Linear Regression functions in Oracle ?

Answer 1

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=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