Homework with Solution - Statistics for Engineers | STAT 4706, Assignments of Statistics

HW 5 Material Type: Assignment; Professor: Williams; Class: Statistics for Engr; Subject: Statistics; University: Virginia Polytechnic Institute And State University; Term: Fall 2006;

Typology: Assignments

Pre 2010

Uploaded on 12/16/2006

g0h0k1e5
g0h0k1e5 🇺🇸

4.8

(6)

41 documents

1 / 3

Toggle sidebar

This page cannot be seen from the preview

Don't miss anything!

bg1
Stat 4706 HW 5 Solutions
Total Points Possible: 23
1) In “Orthogonal Design for Process Optimization and Its Application to Plasma Etching”
(Solid State Technology, May 1987), Yin and Jillie describe an experiment to determine the
effect of C2F6 on the uniformity of the etch on a silicon wafer used in integrated circuit
manufacturing. Three flow rates are used in the experiments, and the resulting uniformity for six
replicates is shown below.
Observations
Flow Rate 1 2 3 4 5 6
125 2.7 4.6 2.6 3.0 3.2 3.8
160 4.9 4.6 5.0 4.2 3.6 4.2
200 4.6 3.4 2.9 3.5 4.1 5.1
a) Using Minitab, generate a boxplot for each of the flow rates (either 3 separate graphs or
all 3 boxplots on 1 graph like in the notes).
flowrate
Y
200
160
125
5.04.54.03.53.02.5
Boxplot of Y vs f lowrate
b) Calculate the SSTreatment, SSError, and SSTotal.
SSTOTAL: 11.278
SSTREATMENT: 3.648
SSERROR: 7.630
c) Complete the ANOVA Table below:
Source SS Df MS F0
Treatment 3.648 3-1 = 2 3.648/2 =
1.824 3.59
Error 7.630 3(6-1) =
15 7.630/15
= 0.509
otal 11.278 17
Worth 2
points
Worth 3 points: each one SS worth 1 point
Worth 3 points:
each df, MS and F
worth 1/2 point each
pf3

Partial preview of the text

Download Homework with Solution - Statistics for Engineers | STAT 4706 and more Assignments Statistics in PDF only on Docsity!

Stat 4706 HW 5 Solutions

Total Points Possible: 23

  1. In “Orthogonal Design for Process Optimization and Its Application to Plasma Etching” ( Solid State Technology, May 1987), Yin and Jillie describe an experiment to determine the effect of C 2 F 6 on the uniformity of the etch on a silicon wafer used in integrated circuit manufacturing. Three flow rates are used in the experiments, and the resulting uniformity for six replicates is shown below. Observations Flow Rate 1 2 3 4 5 6 125 2.7 4.6 2.6 3.0 3.2 3. 160 4.9 4.6 5.0 4.2 3.6 4. 200 4.6 3.4 2.9 3.5 4.1 5.

a) Using Minitab, generate a boxplot for each of the flow rates (either 3 separate graphs or all 3 boxplots on 1 graph like in the notes).

flowrate

Y

200

160

125

2.5 3.0 3.5 4.0 4.5 5.

Boxplot of Y vs flowrate

b) Calculate the SSTreatment, SSError, and SS (^) Total.

SSTOTAL: 11. SSTREATMENT: 3. SSERROR : 7.

c) Complete the ANOVA Table below: Source SS Df MS F 0 Treatment 3.648 3-1 = 2 3.648/2 =

Error 7.630 3(6-1) = 15

otal 11.278 17

Worth 2 points

Worth 3 points: each one SS worth 1 point

Worth 3 points: each df, MS and F worth 1/2 point each

d) Complete a hypothesis test to see if the means of all three flow rates are equal.

H 0 : All of the treatment means are equal. H 1 : At least one of the treatment means is different.

Test Statistic: F=3.

Rejection Region: Reject H 0 if Fcalc > F.05,2,15 = 3.

Decision: Fail to Reject H 0

Conclusion: All of the treatment means are equal.

  1. From the results of an ANOVA test on the equality of 3 means, we have found the there is a difference in the means, but need to identify which ones differ. Use the following Minitab output to determine which means differ.

One-way ANOVA: Score versus Method

Source DF SS MS F P Method 2 416.0 208.0 14.40 0. Error 9 130.0 14. Total 11 546.

S = 3.801 R-Sq = 76.19% R-Sq(adj) = 70.90%

Level N Mean StDev 1 4 72.000 4. 2 4 86.000 4. 3 4 76.000 2.

Means are significantly different if

[ ] [ ] 7. 506975

= , , * = q = = n

HSD q α kv s

2 3

1 3

1 2

y y

y y

y y

[ ]

n

y (^) i yj q kv s

Worth 1 point

Worth 1 point

Worth 1 point

Worth 1 point

Worth 3 points: HSD worth 1. points, identifying significant differences worth 1.5 points