HW 4
HW 4
HW 4
Homework 4
October 6, 2014
4.20 The effect of five different ingredients (A,B,C,D,E) on the reaction time of a chemical process is being
studied. Each batch of new material is only large enough to permit five runs to be made. Furthermore, each
run requires approximately 1 12 hours, so only five runs can be made in one day. The experimenter decides
to run the experiment as a Latin square so that day and batch effects may be systematically controlled. She
obtains the data that follow. Analyze the data from this experiment (use α = 0.05) and draw conclusions.
Day
Batch 1 2 3 4 5
1 A=8 B=7 D=1 C=7 E=3
2 C = 11 E=2 A=7 D=3 B=8
3 B=4 A=9 C = 10 E =1 D=5
4 D=6 C=8 E=6 B=6 A = 10
5 E=4 D=2 B=3 A=8 C=8
Method
Factor Information
Analysis of Variance
Model Summary
Based on the obtained minitab results, we can conclude that the chemical ingredients have a significant effect
the reaction time because it has a p-value of 0. Also, we can conclude that the effects of batch and day are
negligible on reaction time (once they are controlled for) because they both have p-values greater than our
α of .05. The normal probability plot and the residual graphs below do not give us any reason to question
our normality or identical independent assumptions.
4.33 An engineer is studying the mileage performance characteristics of five types of gasoline additives.
In the road test he wishes to use cars as block; however, because of a time constraint, he must use an
incomplete block design. He runs the balanced design with the five blocks that follow. Analyze the data from
this experiment (use α = 0.05) and draw conclusions.
Day
Additive 1 2 3 4 5
1 17 14 13 12
2 14 14 13 10
3 12 13 12 9
4 13 11 11 12
5 11 12 10 8
General Linear Model: Mileage versus Car, Additive
Method
Factor Information
Analysis of Variance
2
Model Summary
Based on the obtained Minitab output, we can conclude that both the car and the gasoline additive have
a statistically significant affect on the mileage as both have p-values of 0.01. The normal probability plot
and the residual graphs included below do not give us any reason to question the normality or identically
independently distributed assumptions. Though it is woth noting that there seems to be some mild grouping
in the NPP.
4.42 Verify that a BIBD with the parameters a = 8, r = 8, k = 4, and b = 16 does not exist.
We know that for a BIBD with those parameters to exist, there must exist an integer λ such that
r(k − 1) 8(4 − 1) 24
λ= = = 6∈ Z
a−1 8−1 7
Therefore, a BIBD does not exist with those parameters.
5.3 The yield of a chemical process is being studied. The two most important variables are thought to be
the pressure and the temperature. Three levels of each factor are selected and a factorial experiment with
two replicates is performed. The yield data are as follows.
Pressure (psig)
Temperature ◦ C 200 215 230
150 90.4 90.7 90.2
90.2 90.6 90.4
160 90.1 90.5 89.9
90.3 90.6 90.1
170 90.5 90.8 90.4
90.7 90.9 90.1
3
a.) Analyze the data and draw conclusions. Use α− = 0.05.
General Linear Model: Yield versus Temp, Pressure
Method
Factor Information
Analysis of Variance
Model Summary
Based on the obtained Minitab output, we would conclude that both pressure and temperature are significant,
since they have p-values that are less than our α of 0.05. However, we would also conclude that the interaction
between pressure and temperature is not significant since the p-value is 0.47, which is larger than our α.
b.) Prepare appropriate residual plots and comment on the model’s adequacy.
The normal probability and residual plots do not give us significant cause to question the normality or
identically distributed assumptions, though it is important to note that there seems to be more of a variation
in the third batches of both temperature and pressure.
4
c.) Under what conditions would you operate this process?
Comparisons for Yield
We see from our Tukey Pairwise Comparisons for Yield that the process should be operated using temperature
3: 170◦ and pressure 2: 215 psig for the highest yield. It is important to note that Tukey did not find a
significant difference between temperature 1 and temperature 3 or temperature 1 and temperature 2, however
we will select temperature 3 both because it has the highest mean yield and because it is statistically
significantly different from temperature 2. This selection is also supported by the contour plot included
below.
5
5.4 An engineer suspects that the surface finish of a meat part is influenced by the feed rate and the depth
of cut. He selects three feed rates and four depths of cut. He then conducts a factorial experiment and obtains
the folowing data:
Method
Factor Information
Analysis of Variance
6
Source DF Adj SS Adj MS F-Value P-Value
Feed Rate 2 3160.5 1580.25 55.02 0.000
Depth of Cut 3 2125.1 708.37 24.66 0.000
Feed Rate*Depth of Cut 6 557.1 92.84 3.23 0.018
Error 24 689.3 28.72
Total 35 6532.0
Model Summary
Based on the obtained Minitab output, we can conclude that both Feed Rate and Depth of Cut are significant
since they have p-values of less than our α of 0.05. We can also declare the interaction between Feed Rate
and Depth of Cut to be significant as it has a p-value of 0.018, which is also less than α.
b.) Prepare appropriate residuals plots and comment on the model’s adequacy.
The normal probability and residual plots do not give us any reason to doubt our normality and independent
identical distribution assumptions.
c.) Obtain point estimates of the mean surface finish at each feed rate.
Fitted
Term Mean SE Mean
Feed Rate
1 81.58 1.55
2 97.58 1.55
3 103.83 1.55
Depth of Cut
1 84.78 1.79
2 89.78 1.79
3 97.89 1.79
4 104.89 1.79
7
We are only interested in the point estimates of the mean surface finish at each feed rate, so we will use a
one-factor plot.
Factor P-Value
Feed Rate 0.000
Depth of Cut 0.000
Feed Rate * Depth of Cut 0.018
5.5 For the data in problem 5.4 compute a 95 percent confidence interval estimate of the mean difference
in response for feed rates of 0.20 and 0.25 in/min.
Feed
Rate N Mean Grouping
3 12 103.833 A
2 12 97.583 B
1 12 81.583 C
Difference
of Feed Difference SE of Simultaneous Adjusted
Rate Levels of Means Difference 95% CI T-Value P-Value
2 - 1 16.00 2.19 (10.54, 21.46) 7.31 0.000
3 - 1 22.25 2.19 (16.79, 27.71) 10.17 0.000
8
3 - 2 6.25 2.19 ( 0.79, 11.71) 2.86 0.023
We are only interested in a 95% confidence interval for the mean difference between levels 1 and 2 of Feed
Rate. Therefore, our desired confidence interval is (10.54, 21.46) e.g. 16 + / − 5.46.
5.20 In Problem 5.3, suppose that we wish to reject the null hypothesis with a high probability if the
difference in the true mean yield at any two pressures is as great as 0.5. If a reasonable prior estimate of
the standard deviation of yield is 0.1, how many should be run?
We know that
a = 3b = 3D = 0.5
Therefore, we can calculate the desired sample size by finding the minimum value of φ2 .
naD2 n ∗ 3 ∗ (0.5)2
φ2 = 2
= = 12.5n
2bσ 2 ∗ (3) ∗ (0.1)2
For a sample size of n = 2, we see that we have a φ = 5. Using the given formulas and the charts available
in Appendix V (the Operating Charecteristic Curves. . . ) we can obtain the following:
n φ2 φ ν1 ν2 β
2 25 5 2 9 ¡ .05
For ν1 = 2 and ν2 = 9, we have a β < 0.05 on the OCC graph. Therefore, a sample size of 2 is sufficient to
detect a difference of 0.5 between pressures.