Scribd
Upload
26 views12 pages

Multiple Regression: Click To Edit Master Subtitle Style

Multiple regression is a statistical technique for estimating the relationship between a continuous dependent variable and two or more independent predictor variables. It is useful when more than one variable can explain or forecast a dependent variable. The value of multiple regression is that it can estimate the relative importance of predictors and assess how combined variables influence changes in the dependent variable. An example is using automobile production and building contracts awarded to predict a glass company's net sales. The method of least squares is used to estimate coefficients that minimize the sum of squared errors by fitting a plane to data points.

Uploaded by

hiranhl
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
26 views12 pages

Multiple Regression: Click To Edit Master Subtitle Style

Multiple regression is a statistical technique for estimating the relationship between a continuous dependent variable and two or more independent predictor variables. It is useful when more than one variable can explain or forecast a dependent variable. The value of multiple regression is that it can estimate the relative importance of predictors and assess how combined variables influence changes in the dependent variable. An example is using automobile production and building contracts awarded to predict a glass company's net sales. The method of least squares is used to estimate coefficients that minimize the sum of squared errors by fitting a plane to data points.

Uploaded by

hiranhl
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 12

Multiple Regression

Click to edit Master subtitle style HIRAN H L FUS 100608 M2, TECH.MANAGEMENT DEPT.OF FUTURES STUDIES

4/28/12

What is Multiple Regression?

Multiple Regression is :

statistical technique for estimating the relationship between a continuous dependent variable and two or more continuous or discrete independent, or predictor variables.
4/28/12

When to use it?

In many decision making situations where:

more than one variable can be used to explain or forecast a certain dependant variable
4/28/12

Importance of multiple regression:

The value of the multiple regression approach lies in its capacity to:

estimate the relative importance of several hypothesized predictors and its ability to assess the contribution of the combined variables to change

4/28/12

Example:
CPG California plate glass, a glass business co.
net sales CPG= f (automobile production, building contracts awarded) Relation between variables can be expressed as: y^= a+b1x1+b2x2
4/28/12

Method:

method of least squares can be used to estimate best fit values for a, b1,b2. but need three axis and 3-dimensional graph try to fit a plane to the data points available
4/28/12

by minimising the sum of squared

Assumptio ns:

first assumption is existence of linear relationship (individual graph on each pair can help) homoscedasticity- constant variace of regression errors (no outliers) residuals are independent of each other (random, no autocorrelation) D-W test (1.5 to 2.5 , AC present) residuals are normally distributed Multicollineartity does not exist among independent variables (range +0.7 to -0.7)
4/28/12

Steps:

formulation of the problem choice of the Economic and other relavant indicators Initial test run on multiple regression Studying the matrix of simple correlation Deciding among Individual regressions
4/28/12

Observing the value of R

Co-efficient of determination:

dependent and predictors combined correlation are to be calculated Individual correlations are also calculated

4/28/12

Tests of significance:

overall test of significance of equation: F test: ratio of the explained variance

to unexplained variance

4/28/12

testing the significance of individual coefficients: t-test:

calculates the standard error of each of the coefficients

uses that error to determine whether the

value of the co-efficient is significantly different from 0


4/28/12

t_test value < t_table value (= 0.05)

THANK YOU

4/28/12

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy