Scribd
Upload
66 views8 pages

Value of One Variable in Terms of The Other Variable

Simple linear regression is used to predict the value of one variable based on another variable. It finds the equation of the regression line that best fits the data points. The document provides an example of using data on students' years of schooling and exam scores to calculate the regression line equation and use it to predict exam scores. It also defines and calculates the standard error of estimate, which measures how far the data points deviate from the regression line.

Uploaded by

SHARMAINE CORPUZ MIRANDA
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
66 views8 pages

Value of One Variable in Terms of The Other Variable

Simple linear regression is used to predict the value of one variable based on another variable. It finds the equation of the regression line that best fits the data points. The document provides an example of using data on students' years of schooling and exam scores to calculate the regression line equation and use it to predict exam scores. It also defines and calculates the standard error of estimate, which measures how far the data points deviate from the regression line.

Uploaded by

SHARMAINE CORPUZ MIRANDA
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/ 8

SIMPLE LINEAR REGRESSION

 
Regression – it is a test used to possibly approximate or predict
value of one variable in terms of the other variable.
 
Equation of the Regression Line:

ypred = mx + b where ypred = the predicted value of y

b= Y – mX

m = [n∑(xy) – ∑x ∑y] / [n∑x2 –(∑x)2]


Example:
Below are the data of 10 out of school youth who took the
placement examination offered by the Department of Education
(DepEd) to those school drop outs who desire to go back to
school. The data show the number of school years the students
had attended and the corresponding placement examination
percentile rank each student had attained.
Solution:

Students No. of Yrs. Percentile Rank x^2 xy


x y
1 4 58 16 232
2 5 79 25 395
3 5 73 25 365
4 3 59 9 177
5 6 90 36 540
6 4 64 16 256
7 5 76 25 380
8 6 85 36 510
9 4 76 16 304
10 3 49 9 147

TOTAL 45 709 213 3306


X= ∑x / n = 45/10 = 4.5
Y = ∑y /n = 709/10 = 70.9
m= [n∑(xy) – ∑x ∑y] / [n∑x2 –(∑x)2]
=[10(3306) – 45 (709)] / [10(213) – 452)
= (33060 – 31905) / (2130 – 2025)
m= 11
b= Y – mX
= 70.9 – 11(4.5)
b = 21.4 
Therefore the equation of the regression line for the given
data is:
ypred = mx + b = 11x + 21.4
*** Use the equation of the regression line to check whether
the visually approximated value of y = 44 when x = 2 is accurate
or nearly accurate.

ypred = 11x + 21.4 = 11 (2) + 21.4 = 43.4


 
*** What is the approximate percentile rank of a student who
attended 3 ½ years in high school?

ypred = 11x + 21.4 = 11 (3.5) + 21.4 = 59.9


 
 
STANDARD EROR OF ESTIMATE (Se)

it is a measure of the amount of spread of the sample points


about the regression line
is shows how the sample points deviate from their regression
line.
 
Se = √( ∑y2 – b ∑y – m ∑xy) / (n-2)
 
Example:
 
Compute the Se for the set of paired data of the 10 out-of-school
youth who took the DepEd placement examination.

Student No. of Yrs. Percentile Rank y2 xy


x Y
1 4 58 3364 232
2 5 79 6241 395
3 5 73 5329 365
4 3 59 3481 177
5 6 90 8100 540
6 4 64 4096 256
7 5 76 5776 380
8 6 85 7225 510
9 4 76 5776 304
10 3 49 2401 147
Total 45 709 51789 3306
Se = √( ∑y2 – b ∑y – m ∑xy) / (n-2)
 
= √ [51789 – 21.4 (709) – 11(3,306)] / (10-2)

= √ (51789 – 15, 192.6 – 36,366) / 8


= √ 31.3
= 5.59
 

You might also like