Oracle PL/SQL Tutorial/Linear Regression Functions/Introduction

Using the Linear Regression Functions

Linear regression functions fit an ordinary-least-squares regression line to a set of number pairs.

You can use the linear regression functions as aggregate, windowing, or reporting functions.

The following table shows the linear regression functions.

In the function syntax, y is interpreted by the functions as a variable that depends on x.

Function Description REGR_AVGX(y, x) Returns the average of x after eliminating x and y pairs where either x or y is null. REGR_AVGY(y, x) Returns the average of y after eliminating x and y pairs where either x or y is null. REGR_COUNT(y, x) Returns the number of non-null number pairs that are used to fit the regression line. REGR_INTERCEPT(y, x) Returns the intercept on the y-axis of the regression line. REGR_R2(y, x) Returns the coefficient of determination, or R-squared, of the regression line. REGR_SLOPE(y, x) Returns the slope of the regression line. REGR_SXX(y, x) Returns REG_COUNT(y, x) * VAR_POP(x). REGR_SXY(y, x) Returns REG_COUNT(y, x) * COVAR_POP(y, x). REGR_SYY(y, x) Returns REG_COUNT(y, x) * VAR_POP(y).

Quote from:

Oracle Database 10g SQL (Osborne ORACLE Press Series) (Paperback)

# Paperback: 608 pages

# Publisher: McGraw-Hill Osborne Media; 1st edition (February 20, 2004)

# Language: English

# ISBN-10: 0072229810

# ISBN-13: 978-0072229813