DP-6 : Multiple linear regression

Abstract

The association of three or more variables can be Investigated by multiple linear regression and correlation analysis. The derivation of relationships among hydrologic variables is of importance for the transfer of information from few gauged stations to many ungauged stations. The general form of the multiple linear regression is

X1= B1 + B2X2+B3X3+……..+BmXm+e

where, X1

is dependent variable and X2, X3, .........Xm

are independent variables. E is the error term.

In the documentation, listing of the source programme for multiple linear regression analysis, input data file and output file is given with test data and example calculations. In the programme the selection of different sets of independent variables and designation of dependent variable can be made as many times as desired.

The programme calculates means, standard derivations of dependent and independent variables, correlation coefficients between dependent and independent variables, regression coefficients, standard error of regression coefficients, computed t-values, intercept, multiple correlation coefficient, standard error of estimate, analysis of variance for multiple regression and table of residuals.