Scribd
Upload
52 views21 pages

Business Statistics

This document is the presentation slides for a business statistics course titled "Regression and Correlation". It discusses the key concepts of regression and correlation as they relate to analyzing the relationship between GPAs and starting salaries of 30 recent college graduates. The regression line calculated from the data is y = 10.31 + 12.67x, indicating starting salary increases by approximately 12,670 Taka for each one point increase in GPA. The coefficient of correlation (r = 0.83) represents a strong positive linear relationship between the variables, while the coefficient of determination (r2 = 0.72) means 72% of the variation in starting salaries is explained by the regression model.

Uploaded by

Desarollo Organizacional
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
52 views21 pages

Business Statistics

This document is the presentation slides for a business statistics course titled "Regression and Correlation". It discusses the key concepts of regression and correlation as they relate to analyzing the relationship between GPAs and starting salaries of 30 recent college graduates. The regression line calculated from the data is y = 10.31 + 12.67x, indicating starting salary increases by approximately 12,670 Taka for each one point increase in GPA. The coefficient of correlation (r = 0.83) represents a strong positive linear relationship between the variables, while the coefficient of determination (r2 = 0.72) means 72% of the variation in starting salaries is explained by the regression model.

Uploaded by

Desarollo Organizacional
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 21

Course no: FB-508

Course title: Business Statistics

Presented To:

Dr. Md. Main Uddin


Associate Professor
Department of Banking & Insurance
University Of Dhaka

Date of presentation: 12.12.2015

Presented by:

Md. Asaduzzaman Munshi 51530071


Md. Masum Billah 51530075
Tanjilal Aziz - 51531004
Fatema Mariom 51531028
Ismatara Ela - 51531016

Title

Regression and Correlation

Regression
Correlation

Regression
and
Correlation
The Following table gives information on GPAs and staring
Salaries (nearest thousand TK) of 30 recent college
graduates:

Calculation Table

Calculation

Calculation

Calculation

Calculation

Calculation

Calculated value

Regression Line
y = 10.31 + 12.67 x
Meaning of the values 10.31 and 12.67:-

The value of a= 10.31 is the value of y for x=0.


This represents that the starting salary is about
10310 TK for a college graduate with GPA of zero.
The value of b= 12.67 means that, on average,
the starting salary of a college graduate
increases by 12670 TK for every 1- point increase
in GPA.

Scatter plot and Regression


line

Other Calculated Value

Coefficient of Correlation, r

Coefficient of Correlation,

r = 0.83
This value indicates that the variables have a
strong positive linear relationship.

Coefficient of Determination, r2
Coefficient of Determination,
r2 = 0.72
This value indicates that 72% of the total
squared errors (SST) are explained by the
regression model.

Prediction Error
We see that if a student having GPA 3.25, he will
get a starting salary of TK 51.48(from the
regression equation) thousand, but the real is 52
thousand TK.
This is called the prediction error.

Standard Deviation Error, Se


Standard deviation error
Se = 4.25
This value indicates that the errors of the value
of y spreading 4.25 around the regression line for
the given
values of x

SST, SSE and SSR

Total Sum of Square, SST = 1831.86

Error Sum of Square, SSE = 507.46

Regression Sum of Square, SSR = 1323.83

The values of SST= 1831.86 and SSE= 507.48


indicate that the sum of squared errors
decreased from 1831.86 to 507.48 when we
used y in place of y to predict starting
salary. This reduction in squared error is SSR.

21

You might also like