Scribd
Upload
68 views3 pages

BRM - 4.4 Measures of Linear Relationship

This document discusses measures of linear relationship between two variables including covariance, coefficient of correlation, least squares method, and coefficient of determination. Covariance measures how variables change together, and coefficient of correlation normalizes covariance by variable standard deviations. Least squares finds the best fit line to minimize residuals. Coefficient of determination quantifies the proportion of dependent variable variation explained by the independent variable.

Uploaded by

Sasin Sasikala
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
68 views3 pages

BRM - 4.4 Measures of Linear Relationship

This document discusses measures of linear relationship between two variables including covariance, coefficient of correlation, least squares method, and coefficient of determination. Covariance measures how variables change together, and coefficient of correlation normalizes covariance by variable standard deviations. Least squares finds the best fit line to minimize residuals. Coefficient of determination quantifies the proportion of dependent variable variation explained by the independent variable.

Uploaded by

Sasin Sasikala
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

BRM- Chapter 4 – Numerical Descriptive Techniques

BRM- 4.4 Measures of Linear Relationship

Covariance: Provides insight into how two


interval variables are related to one another. The
measure of how two random variables in a data
set will change together. A positive covariance
means that two variables at hand are positively
related, and the move in the same direction.

In general when two variables move in the same


direction (both increase or both decrease), the
covariance will be a large positive number.

Coefficient of correlation: The


covariance divided by the standard
deviations of the variables. It has a
upper and lower limit which are -1
and 1.

-1 < = R <= +1

-1 < = P <= +1

Steps of calculating the coefficient of correlation: (P. 129)

1. Calculate sample mean of X dash


2. Calculate sample mean o Y dash
3. Calculate variance of X
4. Calculate the variance of Y
5. Root the sum of Variances of X for the standard deviation
6. Root the sum of Variances of Y for the standard deviation
7. Sample covariance/ (Sample standard deviations x) (Sample variance)

 The scatter diagram depicts the relationship graphically.


 The covariance and the coefficient of correlation describe the linear relationship numerically.
 E.g. The covariance and coefficient of correlation can be 34.87 and .9641, this will tell us
something about a strong positive relationship between two variables. Vice versa. Negative
and strong relationship with -34.18 and -.8791. Covariance of 2.07 and .1206 no apparent
linear relationship.

1
Least squares method: A statistical
procedure to find the best fit for a set of
data points by minimising the sum of the
offsets or residuals of the points from the
plotted curve.

B0: Is the intercept Y (where he line


intercepts the y- axis)

B1: The slope (defined as rise/run) and Y


hat s the value of y determined by the
line.

Y hat = B0 + B1x

The coefficients b0 and b1x are derived using


calculus.

Steps of calculating the coefficient of


correlation: (P. 134)

1. Determine the dependent and


independent variable.
2. SUM the X, Y, XY, X2 and Y2  Make the table!
3. Calculate the covariance
4. Calculate the variance of X
5. Calculate the sample means of dash x and dash y
6. Calculate the slope of the least square lines !  B1= Covariance/ Variance of X
7. Calculate the Y-intercept  B0= Y mean – (slope)(x dash) = Y intercept
8. Formulate the Least square line. Y hat= 9.57 + 2.25x

 The slope is defined as rise/run, which means that it is the change in y (rise) for one- unit
increase in x (run). The slopes measures the marginal rate of change in the dependent
variable. The marginal rate of change refers to the effect of increasing the independent
variable by one additional unit.

2
Steps of calculating the strength of the linear relationship (P. 137)

1. Have the covariance and the variance of X.


2. Covariance Sxy = 36.06
3. Variance of x= sx2 = 16.06
4. Standard deviation of x is sx root the variance= 4.01
5. Variance of S2y  106.73
6. Root the variance of Sy= 10.33
7. The coefficient of correlation is Sxy / sxsy = 36.06/ (4.01)(10.33)

Coefficient of determination: Is a measurement used to explain how much variability of one factor
can be caused by its relationship to another related factor. This correlation is known as the goodness
of fit, is represented as a value between 0 and 1. R 2 also the square root of the coefficient of
correlation.

 If the coefficient of correlation is -1 or 1, a scatter diagram would display all the points lining
up in a straight line. The coefficient of determination is 1, which we interpret to mean that
100% of the variation in the dependent variable Y is explained by the variation in the
independent variable x.
 If the coefficient of correlation is 0 then there is no linear relationship between the two
variables R2 .
 In example 4.18 (page 139) the coefficient of correlation was calculated to be r= .8711.
Thus, the coefficient of determination is r2= (.8711) = .7588, meaning that 75.88% of the
variation in electrical costs is explained by the number of tools. The remaining 24.12% is
unexplained.

Coefficient of correlation: If two interval variables are linearly related, it does not mean that X causes
Y. It may mean that another variable causes both X and Y or that Y causes X. Remember correlation
is not causation!!!!!

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