In: Statistics and Probability
Wenton Powersports produces dune buggies. They have three assembly lines, “Razor,” “Blazer,” and “Tracer,” named after the particular dune buggy models produced on those lines. Each assembly line was originally designed using the same target production rate. However, over the years, various changes have been made to the lines. Accordingly, management wishes to determine whether the assembly lines are still operating at the same average hourly production rate. Production data (in dune buggies/hour) for the last eight hours are as follows. (You may find it useful to reference the F table.)
Razor | Blazer | Tracer | ||||||||
12 | 10 | 9 | ||||||||
11 | 8 | 9 | ||||||||
9 | 11 | 10 | ||||||||
10 | 9 | 9 | ||||||||
9 | 11 | 8 | ||||||||
9 | 10 | 7 | ||||||||
13 | 11 | 8 | ||||||||
11 | 8 | 9 | ||||||||
a. Specify the competing hypotheses to test whether there are some differences in the mean production rates across the three assembly lines.
H0: μRazor = μBlazer = μTracer. HA: Not all population means are equal.
H0: μRazor ≤ μBlazer ≤ μTracer. HA: Not all population means are equal.
H0: μRazor ≥ μBlazer ≥ μTracer. HA: Not all population means are equal.
b-1. Construct an ANOVA table. Assume production rates are normally distributed. (Round intermediate calculations to at least 4 decimal places. Round "SS" to 2 decimal places, "MS", "p-value" to 4 decimal places, and "F" to 3 decimal places.)
ANOVA | |||||||
Source of Variation | SS | df | MS | F | p-value | F crit | |
Between Groups | |||||||
Within Groups | |||||||
Total |
b-2. At the 5% significance level, what is the
conclusion to the test?
(Reject, Do not reject) HO, we (can, cannot) conclude that the mean buggies/hour differ for some production lines.
b-3. What about the 10% significance level?
(Reject, Do not reject) HO, we (can, cannot) conclude that the mean buggies/hour differ for some production lines.
Given :
Production data (in dune buggies/hour) for the last eight hours are as follows.
Razor | Blazer | Tracer | ||||||||
12 | 10 | 9 | ||||||||
11 | 8 | 9 | ||||||||
9 | 11 | 10 | ||||||||
10 | 9 | 9 | ||||||||
9 | 11 | 8 | ||||||||
9 | 10 | 7 | ||||||||
13 | 11 | 8 | ||||||||
11 | 8 | 9 | ||||||||
a) Hypothesis test :
The null and alternative hypothesis is
H0: μRazor = μBlazer = μTracer.
HA: Not all population means are equal.
b-1) Data summary :
Using software
Groups | N | Mean | Std.Dev | Std error |
1 | 8 | 10.5 | 1.5119 | 0.5345 |
2 | 8 | 9.75 | 1.2817 | 0.4532 |
3 | 8 | 8.625 | 0.9161 | 0.3239 |
ANOVA table :
Source | df | SS | MS | F | P-VALUE |
Between groups | k-1= 3-1 =2 | 14.25 | SSB/df1 = 7.1250 | SSB/SSW = 4.483 | 0.0239 |
Within Groups | N-k = 24-3 = 21 | 33.37 | SSW/df2 = 1.5893 | ||
Total | 23 | 47.62 |
b-2) Since P-value is less than significance level 0.05, we reject the null hypothesis.
Conclusion : At 5% significance level, reject Ho. We can conclude that the mean buggies/hour differ for some production lines.
b-3) Since P-value is less than significance level 0.10, we reject the null hypothesis.
Conclusion : At 10% significance level, reject Ho. We can conclude that the mean buggies/hour differ for some production lines.