Scribd
Upload
3 views1 page

Multiple Linear Regression Analysis Guide

Multiple linear regression allows predicting values of a dependent variable based on independent variables. The general formula is the predicted value equals a constant plus the product of each independent variable and its coefficient. Degrees of freedom are counts of values free to vary in calculations. An example output shows a regression predicting consumption from population, GDP, and electricity price, with R-squared of 0.994 indicating the model explains 99.4% of the variance in consumption.

Uploaded by

Ahmad Elayyan
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
3 views1 page

Multiple Linear Regression Analysis Guide

Multiple linear regression allows predicting values of a dependent variable based on independent variables. The general formula is the predicted value equals a constant plus the product of each independent variable and its coefficient. Degrees of freedom are counts of values free to vary in calculations. An example output shows a regression predicting consumption from population, GDP, and electricity price, with R-squared of 0.994 indicating the model explains 99.4% of the variance in consumption.

Uploaded by

Ahmad Elayyan
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Multiple Linear Regression:

General Formula: = 0 + 1 x1i + 2 x2i + 3 x3i + i

Degrees of Freedom (df):


df (R) = The number of independent variables (k),
df (T) = n 1,
df (E) = n 1 k

For an example, given the following SPSS table:


Coefficientsa
Standardized
Unstandardized Coefficients
Model Coefficients t Sig.
Std. Error Beta

Constant 175.483 607.108 0.289 0.776


Population
(Thousands)
-0.193 0.151 -0.189 -1.278 0.216
GDP
(Thousands)
0.608 0.059 1.081 10.250 0.000
Electricity Price
Fills\KWH
-14.787 5.679 -0.183 -2.604 0.017

a. Dependent Variable: Consumption (GWH)

The general formula would be: = 175.483 + -0.193 x1i + 0.608 x2i + -14.787 x3i + 84.06842

Model Summery
Std. Error Change Statistics
Adjusted R
Model R R Square of the R Square Sig. F
Square F Change df1 df2
Estimate Change Change

1 .997a .994 .993 84.06842 .994 1060.086 3 20 .000

a. Predictors: (Constant), Electricity price (fills\KWH), GDP (Thousand), Population (Thousands)

Coefficient of Determination = R2 = 0.994, Correlation Coefficient = R = 0.997


When choosing between models, the model with the least mean square errors (MSE) is
the best.

You might also like