Scribd
Upload
23 views11 pages

Module 4.0 Improve Phase - 4.1 Simple Linear Regressions

This document provides an overview of the Improve Phase of a project and discusses simple linear regression and multiple linear regression. It covers correlation analysis, regression equations, residual analysis, and examples of simple linear regression including calculating a regression equation and evaluating the model using R-squared, ANOVA, and residual analysis.

Uploaded by

Stackwell India
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
23 views11 pages

Module 4.0 Improve Phase - 4.1 Simple Linear Regressions

This document provides an overview of the Improve Phase of a project and discusses simple linear regression and multiple linear regression. It covers correlation analysis, regression equations, residual analysis, and examples of simple linear regression including calculating a regression equation and evaluating the model using R-squared, ANOVA, and residual analysis.

Uploaded by

Stackwell India
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
You are on page 1/ 11

MODULE 4.

IMPROVE PHASE
Improve Phase – Overview and Objectives

By the end of this phase, you will be able to:

• Explain Simple Linear Regression

• Discuss Multiple Linear Regression


Simple Linear Regression – Session Overview and Objectives

By the end of this session, you will able to:

• Define Correlation Analysis

• Explain Regression Equation

• Describe Residual Analysis


Analyse Phase - Correlation coefficient

• Correlation coefficient is used to quantify relationship between two continuous variables and denoted by
the symbol r.

• Correlation coefficient is used in the Analyze Phase of Six Sigma Projects to quantify causal relationship
between a continuous X and a Continuous Y variable.

• The r value varies between -1 and +1, -1 < r <+1

• r value of -1 indicates very strong negative correlation and a r value of +1 shows a very strong positive
correlation.

• r value of 0 indicates no correlation at all.


Analyse Phase - Regression

• When r = 1 or r = -1, all points fall on a straight line; when r = 0, they are scattered and give no
evidence of a linear relationship. Any other value of r suggests the degree to which the points
tend to be linearly related.
Simple Linear Regression

Only a single predictor variable or independent variable ‘X’ (e.g.: cutting speed) and a response variable
or dependent variable ‘Y’ (e.g: tool life).

The simple linear regression model is

Yi = β0 + β1 xi + εi i=1,2,...,n

where β0 is the intercept and β1 is the slope of the line and εij is the random error.
Simple Linear Regression – Example

A study was performed on wear of a bearing Y and its relationship to X1 = oil viscosity . The following data
were obtained. Fit a simple regression model to the data (Y vs. X1)  = 0.05

Regression Analysis: Y versus X1


Y X1
The regression equation is 193 1.6
Y = 228 - 2.86 X1
230 15.5
Predictor Coef SE Coef T P 172 22.0
Constant 227.83 26.01 8.76 0.001 91 43.0
X11 -2.8560 0.8780 -3.25 0.031
113 33.0
S = 31.1112 R-Sq = 72.6% R-Sq(adj) = 65.7%
About 66% Wear can be 125 40.0
predicted by oil viscosity
Analysis of Variance

Source DF SS MS F P
Regression 1 10240 10240 10.58 0.031
There is a regression
Residual Error 4 3872 968 between Wear and oil
Total 5 14112 viscosity
Simple Linear Regression – Example
Coefficient of Determination (R2)

Analysis of the validity of Regression Equation

The regression equation is y = 400 - 0.231 X2

P value of X2 factor is 0.015 - Means X2 is a significant X

P value of regression equation as per ANOVA table is 0.015 - Means the equation is valid

R sq adj value is 75.9 - Means only 76% of variation in Y is because of X2. Some other factors also
contribute to the variation.

Need to look for more potential X.2 adj should be min 85%
Coefficient of Determination (R2)

Residual Analysis:

Normal Probability Plot - Looks normal - ok

Residual vs Fits - Randomly above and below the line with no trends - ok

Histogram - shows a normal distribution - ok

Residual vs Time order - Randomly above and below the line with no trends - ok

Overall conclusion: The regression equation is valid, but X2 accounts for only 76% of variation in Y
Summary – Simple Linear Regression

In this session, you learnt about :

• Correlation Analysis

• Regression Equation

You might also like