CLB20903 JULY 2019

1
CLB20903 JULY 2019

100
ASSIGNMENT
DATELINE: 13 November 2019 (Wednesday) by 12 noon.
Please submit to your tutorial lecturer accordingly.

Instructions

(1) Form a group of three (3) (four maximum).

(2) Please answer ALL questions.
(3) Prepare your answers on A4 paper.
(4) Include relevant MINITAB output for each question.
(5) Number your answers accordingly.
(6) One answer booklet should be submitted per group.

Question 1

Tests of product quality using inspectors can lead to serious error problems.
Benson and Ohta (1986) evaluated the performance of inspectors in a new
company using novice and experienced inspectors. Each inspector classified 200
products as defective or non defective. The number of errors is shown as follows:

Novice Experienced
25 35 26 40 46 20 31 15 25 19 28 17
45 31 33 29 21 49 19 18 24 10 20 21

(a) Test the difference between using novice and experienced inspectors. Use
α = 0.01 and assume unequal variances.

(i) Include a relevant MINITAB output.

(5 marks)
(ii) By referring to the output, conclude the hypothesis of the difference
between using novice and experienced inspectors. Follow the step
by step flow of hypothesis testing.
(5 marks)

2
CLB20903 JULY 2019

(b) Test the difference between using novice and experienced inspectors. Use
α = 0.05 and assume equal variances.

(i) Include a relevant MINITAB output.

(5 marks)

(ii) By referring to the output, conclude the hypothesis of the difference

between using novice and experienced inspectors. Follow the step
by step flow of hypothesis testing.
(5 marks)
Question 2

An experiment was conducted to investigate leaking current in a SOS MOSFETS

device. The purpose of the experiment was to investigate how leakage current
varies as the channel length changes. Four channel lengths were selected. For
each channel length, five different widths were also used. The data are as
follows:

Width
Channel Length
1 2 3 4 5
1 0.7 0.8 0.7 0.9 1.0
2 0.8 0.8 0.9 0.9 1.0
3 0.9 1.0 1.7 1.9 4.0
4 1.0 1.6 2.0 3.0 3.5

(a) Test the hypothesis that mean leakage voltage does not depend on the
channel length, use α=0.05.

(i) Include a relevant MINITAB output.

(5 marks)

3
CLB20903 JULY 2019

(ii) By referring to the output, conclude the hypothesis that mean

leakage voltage does not depend on the channel length. Follow the
step by step flow of hypothesis testing.
(5 marks)

(b) Calculate a 99% confidence interval for the mean width of Channel Length
2.
(5 marks)

(c) Calculate a 90% confidence interval for the difference between mean width
of Channel Length 1 and 4.
(5 marks)

Question 3

In a chemical process, batches of liquid are passed through a bed containing an

ingredient that is absorbed by the liquid. In an attempt to relate the absorbed
percentages of the ingredient (y) to the amount of liquid in the batch (x), Bissell
(1992) give the data in the following table:
y x y x
310 4.52 760 6.63
330 5.18 800 5.48
370 5.76 810 6.22
400 5.10 910 5.88
450 6.09 1020 6.99
490 5.55 1020 6.30
520 5.46 1160 6.86
560 5.80 1200 6.73
580 5.50 1230 6.38
650 5.25 1380 7.17
650 6.12 1460 7.23
650 5.92 1490 6.62

(a) By using MINITAB, draw a scatter plot of the data. Label accordingly.
(5 marks)

4
CLB20903 JULY 2019

(b) Perform appropriate analysis and include a relevant MINITAB output.

(5 marks)

(c) By referring to the output, perform hypothesis testing on the significance of

slope (β1) of the model. Use α=0.05. Follow the step by step flow of
hypothesis testing.
(5 marks)

(d) By referring to the output, calculate a 95% confidence interval for β 1.

(5 marks)

Question 4

(a) An experiment with artillery shells yields the following data on the
characteristics of lateral deflections and ranges.

Lateral deflection
Range (meters)
Left Normal Right
0-1,999 6 14 8
2,000-5,999 9 11 4
6,000-11,999 8 17 6
By using α=0.01, test whether the deflection and range are independent.

(i) Include a relevant MINITAB output.

(5 marks)

(ii) By referring to the output, conclude whether the deflection and

range are independent. Follow the step by step flow of hypothesis
testing.
(5 marks)

(b) The number of defects in printed circuit boards is hypothesized to follow a

Poisson distribution. A random sample of n=60 printed boards has been

5
CLB20903 JULY 2019

collected. The following table shows the number of defects observed and
the probability (from Poisson distribution) associated with it.
Number of Observed
Probability
defects frequency
0 32 0.472
1 15 0.354
2 9 0.133
3 4 0.041

By using α=0.05, test whether the number of defects in printed circuit

boards follows a Poisson distribution.

(i) Include a relevant MINITAB output.

(5 marks)

(ii) By referring to the output, conclude whether the number of defects

in printed circuit boards follows a Poisson distribution. Follow the
step by step flow of hypothesis testing.
(5 marks)
Question 5

An experiment studied how three active ingredients of a particular food affect the
overall taste of the product. The measure of the overall taste is the overall mean
liking score (MLS). The three ingredients are identified by the variables X1, X2
and X3. The data (in coded units for the factors) are shown in the following table.
Run X1 X2 X3 MLS
1 -1 0 -1 6.3261
2 0 0 0 6.2444
3 0 0 0 6.5909
4 -1 1 0 6.3409
5 0 1 1 5.9070
6 1 0 -1 6.4880
7 0 -1 1 5.9773
8 1 0 1 6.8605
9 -1 -1 0 6.0455
10 -1 0 1 6.3478
11 0 -1 -1 6.7609

6
CLB20903 JULY 2019

12 0 0 0 5.7727
13 0 1 -1 6.1805
14 1 1 0 6.4894
15 1 -1 0 6.8182
(a) Fit a response surface model (box-behnken) to the data. Include a
relevant MINITAB output.
(5 marks)

(b) From the output, conclude on the significance of the individual variable X1,
X2 and X3. Use α=0.05.
(3 marks)

(c) From the output, conclude on the significance of the regression model,
quadratic terms, interactions and lack-of-fit. Use α=0.05.
(4 marks)

(d) Construct contour plots and response surface plots for MLS. Insert your
suggestions.
(8 marks)