In: Statistics and Probability
Engineers are testing company fleet vehicle fuel economy (miles
per gallon) performance by using different types of fuel. One
vehicle of each size is tested. Does this sample provide sufficient
evidence to conclude that there is a significant difference in
treatment means?
87 Octane | 89 Octane | 91 Octane | Ethanol 5% | Ethanol 10% | |
Compact | 30.8 | 28.4 | 17.7 | 30.7 | 31.1 |
Mid-Size | 17.0 | 19.9 | 20.1 | 17.1 | 31.4 |
Full-Size | 28.9 | 29.0 | 20.4 | 27.0 | 31.3 |
SUV | 21.9 | 22.8 | 19.5 | 18.7 | 29.6 |
(b) Fill in the boxes. (Round your SS
values to 3 decimal places, F values to 2 decimal places,
and other answers to 4 decimal places.)
Two-Factor ANOVA | |||||
Source | SS | df | MS | F | p-value |
Treatments (Fuel Type) | |||||
Blocks (Vehicle Size) | |||||
Error | |||||
Total | |||||
Group | Mean | n | Std. Dev |
87 Octane | |||
89 Octane | |||
91 Octane | |||
Ethanol 5% | |||
Ethanol 10% | |||
Compact | |||
Mid-Size | |||
Full-Size | |||
SUV | |||
Total | |||
Null Hypothesis:
: There is no difference among the fuel type in terms of fuel economy
: There is a difference amongst at least one pair
: There is no difference among the Vehicle types in terms of Fuel economy
: There is a difference amongst at least one pair
Level of significance:
Let us now form this table for calculating Totals and the Sum of squares.
87 Octane | 89 Octane | 91 Octane | Ethanol 5% | Ethanol 10% | Total | |
Compact | 30.8 | 28.4 | 17.7 | 30.7 | 31.1 | 138.7 |
Mid-Size | 17 | 19.9 | 20.1 | 17.1 | 31.4 | 105.5 |
Full-Size | 28.9 | 29 | 20.4 | 27 | 31.3 | 136.6 |
SUV | 21.9 | 22.8 | 19.5 | 18.7 | 29.6 | 112.5 |
Total | 98.6 | 100.1 | 77.7 | 93.5 | 123.4 | 493.3 |
Grand total (GT) =sum of all observation=493.3, Number of observation(n)=20, Number of treatments(t)=5 and Number of blocks(b)=4
1. Correction factor :
2.Total Sum of squares(TSS):
To get the sum of squares of individual values, we form the table of Squares below and add all values:
87 Octane | 89 Octane | 91 Octane | Ethanol 5% | Ethanol 10% | Total | |
Compact | 948.64 | 806.56 | 313.29 | 942.49 | 967.21 | 3978.19 |
Mid-Size | 289 | 396.01 | 404.01 | 292.41 | 985.96 | 2367.39 |
Full-Size | 835.21 | 841 | 416.16 | 729 | 979.69 | 3801.06 |
SUV | 479.61 | 519.84 | 380.25 | 349.69 | 876.16 | 2605.55 |
Total | 2552.46 | 2563.41 | 1513.71 | 2313.59 | 3809.02 | 12752.19 |
3.Treatment Sum of squares(Trss):
Where is the treatment total for treatment.
4. Block sum of squares: (BSS):
Where is the treatment total for Block
5. Error SS(ESS):
Source | SS | df | MS | F | p-value |
Treatments(Fuel Type) | 169.906 | 3 | 56.5018 | 4.66 | 0.0221 |
Blocks(Vehicle Size) | 270.023 | 4 | 67.5058 | 5.57 | 0.0090 |
Error | 145.417 | 12 | 12.1181 | ||
Total | 584.946 | 19 |
Since p-value for treatments<0.05, this sample provide sufficient evidence to conclude that there is a significant difference in treatment means.
Group | Mean | n | Stdev |
87 Octane | 24.65 | 4 | 6.3763 |
89 Octane | 25.025 | 4 | 4.4124 |
91 Octane | 19.425 | 4 | 1.2093 |
Ethanol 5% | 23.375 | 4 | 6.5327 |
Ethanol 10% | 30.85 | 4 | 0.8426 |
Compact | 27.74 | 5 | 2.2361 |
Mid-Size | 21.1 | 5 | 2.2361 |
Full-Size | 27.32 | 5 | 2.2361 |
SUV | 22.5 | 5 | 2.2361 |
Total | 20.55 | 20 | 5.5486 |