You are on page 1of 11

Case 1 – Number 2

The following data give information on the ages (in years) and
the number of breakdowns during the past month of a sample of seven
machines at a large company.

Age of Machines 12 7 2 8 13 9 4

No. of Breakdowns 9 5 1 4 11 7 2
Case 1 – Number 2
a.) What is the independent variable? What is the dependent variable?
b.) Do you expect β to be negative or positive? Why?
c.) Fit a least squares line from which we can predict number of breakdowns
in terms of the age. Is the sign of b as you hypothesized for β?
d.) Plot a scatter diagram of the data and superimpose the regression line.
e.) Give a brief interpretation of the values a and b.
f.) Construct a 95% confidence interval for β and explain in words what
quantity is thus being estimated.
g.) Determine the coefficient of determination and interpret.
Solution
• Age of Machines – Independent Variable
• No. of Breakdown – Dependent Variable

Age of Machines 12 7 2 8 13 9 4
(x)
No. of Breakdowns 9 5 1 4 11 7 2
(y)
No. of Breakdowns vs. Age of Machines
12
Number of Breakdowns

10
y = 0.8916x - 1.4337
R² = 0.9459
8

6
Series1
4 Linear (Series1)

0
0 2 4 6 8 10 12 14
Age of Machine
No. of Breakdowns vs. Age of Machines
12
Number of Breakdowns

10
y = 0.8916x - 1.4337
R² = 0.9459
8

6 Value a is the intercept. It is the value of y (No. of


Series1
4 breakdowns) when x (Age of machine) is 0 (zero). Linear (Series1)

0
0 2 4 6 8 10 12 14
Age of Machine
No. of Breakdowns vs. Age of Machines
12
Number of Breakdowns

10
y = 0.8916x - 1.4337
R² = 0.9459
8

6 Value b is the slope of the line. It is the estimated No.


Series1
4 of breakdowns for every unit of x (Age of machine). Linear (Series1)

0
0 2 4 6 8 10 12 14
Age of Machine
No. of Breakdowns vs. Age of Machines
12
Number of Breakdowns

10
y = 0.8916x - 1.4337
R² = 0.9459
8

6 R² is called the coefficient of determination. It is a


Series1
4 statistical measure of how close the data are to Linear
the (Series1)
2
fitted regression line.
0
0 2 4 6 8 10 12 14
Age of Machine
At 95% confidence interval, α = 0.05
𝑡𝑛−2,𝛼 = 𝑡5,0.025 = 2.571
2

Point estimate ± margin of error


𝑠 𝑠
𝑏 − 𝑡𝑛−2,𝛼 < 𝛽 < 𝑏 + 𝑡𝑛−2,𝛼
2 𝑆𝑥𝑥 2 𝑆𝑥𝑥

0.6465 < 𝛽 < 1.1367

This is the range of likely values for the population parameter.


SUMMARY OUTPUT FROM EXCEL

Regression Statistics
Multiple R 0.972569325
R Square 0.945891091
Adjusted R Square 0.935069309
Standard Error 0.928789859
Observations 7
SUMMARY OUTPUT FROM EXCEL

ANOVA
df SS MS F Significance F
Regression 1 75.4010327 75.40103 87.40623 0.000235848
Residual 5 4.313253012 0.862651
Total 6 79.71428571
SUMMARY OUTPUT FROM EXCEL

Coefficients Standard Error


Intercept -1.43373494 0.827444232
Age of Machine (x) 0.891566265 0.095363558

t Stat P-value Lower 95% Upper 95%


Intercept -1.73273 0.143686 -3.560748052 0.693278173
Age of Machine (x) 9.34913 0.000236 0.646426436 1.136706095

You might also like