Scribd
Upload
16 views3 pages

La Régression Linéaire

Uploaded by

salmaelbied123
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
16 views3 pages

La Régression Linéaire

Uploaded by

salmaelbied123
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

Version anglais

Linear regression:
1/ Definition of variables:
• Dependent variable: pre-assembly cycle time (seconds).
• Independent variable: waiting time due to a supply delay.
2/ Data collection :

Waiting time due to a supply Pre-assembly cycle time (s)


delay (s)
6 16
7 17
0 10
-5 5
-5 5
-1 9

18
16
Pre-assembly cycle time

14
12
10
8
6
4
2
0
-6 -4 -2 0 2 4 6 8

Waiting time due to supply delay

3/ Calculation of linear regression:

Simple linear regression follows the equation:

Y = a + b.X
Where:
• Y: the dependent variable (pre-assembly cycle time).
• X: the independent variable (waiting time due to a supply delay).
• A : the intercept (constant).
• B: the slope of the regression line (coefficient).
With:
B = COV (X, Y) / V(X) such that:
 COV (X, Y) = mean (XY) - mean(X) * mean(Y)
 V(X) = mean(X²) - (mean(X)) ²
Refer to the Excel table for the calculations.

Based on the calculations, we can conclude the regression line equation:

Y = 10 + 1.X
Interpretation
 Slope (B) = 1: This means that for every additional second of waiting time
due to a supply delay, the pre-assembly cycle time increases by 1 second.
 Intercept (A) = 10: This represents the pre-assembly cycle time when
the waiting time is zero (i.e., there is no supply delay). The initial cycle
time would be approximately 10 seconds.

25

20

15

10

0
-6 -4 -2 0 2 4 6 8 10 12
4/ Measuring data quality:

To assess this, I calculate the linear correlation coefficient (r):

R = COV (X, Y) / [√(V(X)) * √(V(Y))]


From the calculations: r = 1 = 100%
Interpretation:
The correlation is positive since r > 0. Furthermore, r = 1 indicates that 100% of
the variation in the pre-assembly cycle time is explained by the variation in
waiting time due to a supply delay.

You might also like