Categories:: Aggregate functions (Linear Regression) , Window functions

REGR_R2¶

Returns the coefficient of determination for non-null pairs in a group. It is computed for non-null pairs using the following formula:

NULL                 if VAR_POP(x) = 0, else
1                    if VAR_POP(y) = 0 and VAR_POP(x) <> 0, else
POWER(CORR(y,x), 2)

Copy

Where x is the independent variable and y is the dependent variable.

Syntax¶

Aggregate function

REGR_R2(y, x)

Copy

Window function

REGR_R2(y, x) OVER ( [ PARTITION BY <expr3> ] )

Copy

Arguments¶

y: The dependent variable. This must be an expression that can be evaluated to a numeric type.
x: The independent variable. This must be an expression that can be evaluated to a numeric type.
expr3: This is the optional expression used to group rows into partitions.

Important

Note the order of the arguments; the dependent variable is first.

Usage notes¶

DISTINCT is not supported for this function.
When used as a window function:
- This function does not support:
  ORDER BY sub-clause in the OVER() clause.
  
  Window frames.

Examples¶

create or replace table aggr(k int, v decimal(10,2), v2 decimal(10, 2));
insert into aggr values(1, 10, null);
insert into aggr values(2, 10, 11), (2, 20, 22), (2, 25,null), (2, 30, 35);

Copy

select k, regr_r2(v, v2) from aggr group by k;

---+----------------+
 k | regr_r2(v, v2) |
---+----------------+
 1 | [NULL]         |
 2 | 0.9976905312   |
---+----------------+

Copy