X- value Y-value or observed cost y-value or Predicted cost
Quarter Machine Hours Maintenance cost X2 XY y (Y-y)2
1 100,000 $ 205,000 10,000,000,000 20,500,000,000 200,225 $ 22,802,343
2 120,000 $ 240,000 14,400,000,000 28,800,000,000 237,815 $ 4,775,325
3 110,000 $ 220,000 12,100,000,000 24,200,000,000 219,020 $ 960,823
4 130,000 $ 260,000 16,900,000,000 33,800,000,000 256,610 $ 11,494,051
5 95,000 $ 190,000 9,025,000,000 18,050,000,000 190,827 $ 684,488
6 115,000 $ 235,000 13,225,000,000 27,025,000,000 228,417 $ 43,332,384
7 105,000 $ 215,000 11,025,000,000 22,575,000,000 209,622 $ 28,919,634
8 125,000 $ 255,000 15,625,000,000 31,875,000,000 247,212 $ 60,649,358
9 105,000 $ 210,000 11,025,000,000 22,050,000,000 209,622 $ 142,656
10 125,000 $ 245,000 15,625,000,000 30,625,000,000 247,212 $ 4,893,963
11 115,000 $ 200,000 13,225,000,000 23,000,000,000 228,417 $ 807,541,019
1,245,000 2,475,000 142,175,000,000 282,500,000,000 Substitute X-value into the 986,196,043
n = 11 regression equation
ΣX ΣY ΣX2 ΣXY Σ(Y-y)2
225,000
Average Y or Y̅
Economic plausibility
A positive relationship between maintenance cost and machine-hours is economically plausible
Goodness of fit
>>> Coefficient of Determination
r2 = 0.82
82% of the variation in maintenance cost can be explained by the machine hours
Note:
Goodness of fit has meaning only if the relationship between the cost drivers and costs is economically plausible
Generally, an r2 of 0.30 or higher passes the goodnessof-fit test
>>> Standard Error of Regression
S= $ 10,467.92
The standard error of $10,467.92 is an estimate of the variation of the observed maintenance costs about the regression line
Note:
The smaller the standard error of the regression, the better the fit and the better the predictions for different values of X
Excellent goodness of fit.
Significance of independent variable
Standard error of the estimated coefficient indicates how much the estimated value, b, is likely to be affected by random factors
Standard error of the estimated coefficient =
Standard error of the estimated coefficient = 0.2944756002
The t-value (t Stat in the Excel output) of a coefficient measures how large the value of the estimated coefficient is relative to its standard error
the value of the estimated coefficient (or b)
t-value =
s
1.8795
t-value =
0.2944756002
t-value = 6.38
It is typical to look for a 5% level of significance, which indicates that there is less than a 5% probability that random factors could have affected the coefficient b
The cutoff t-value at the 5% significance level and 9 degrees of freedom (n-2) is 2.262 --> two-tails
How to check cutoff t-value --> [Link]
Because the t-value for the slope coefficient b is 6.38, which exceeds 2.262, we can conclude that
there is a statistically significant relationship between machine-hours and maintenance cost
(Y-Y̅)2 Estimating the Regression Line
$ 400,000,000
$ 225,000,000
$ 25,000,000
$ 1,225,000,000 a= 12,275
$ 1,225,000,000
$ 100,000,000
$ 100,000,000
$ 900,000,000
$ 225,000,000 b= 1.8795
$ 400,000,000
$ 625,000,000 y = 12,275 + 1.8795x
5,450,000,000
Σ(Y-Y̅)2
ffected the coefficient b
Quarter Machine Hours Maintenance cost 300000
1 100,000 $ 205,000
2 120,000 $ 240,000 250000
3 110,000 $ 220,000
4 130,000 $ 260,000 200000
5 95,000 $ 190,000
150000
6 115,000 $ 235,000
7 105,000 $ 215,000
100000
8 125,000 $ 255,000
9 105,000 $ 210,000
50000
10 125,000 $ 245,000
11 115,000 $ 200,000 0
0 100000 200000
SUMMARY OUTPUT
Regression Statistics Goodness of fit
Multiple R 0.90501193229 Significance of independent variable
R Square 0.81904659758
Adjusted R Square 0.79894066398
Standard Error 10467.9194747
Observations 11
ANOVA
df SS MS F Significance F
Regression 1 4463803956.83453 4463803957 40.73656135 0.0001278754
Residual 9 986196043.165468 109577338.1
Total 10 5450000000
Coefficients Standard Error t Stat P-value Lower 95% Upper 95% Lower 95.0%
Intercept 12275.1798561 33478.3920955974 0.366659779 0.722344863 -63458.204622 88008.56433 -63458.20462
Machine Hours 1.87949640288 0.29447560016967 6.382519984 0.000127875 1.2133463147 2.545646491 1.2133463147
y = a + bx
y = 12275,18 + 1,88 x
200000
Upper 95.0%
88008.564334
2.5456464911
