Statistics For Engineering And The Sciences 5th Edition Mendenhall Solutions Manual download
Statistics For Engineering And The Sciences 5th Edition Mendenhall Solutions Manual download
https://testbankdeal.com/product/statistics-for-engineering-and-the-
sciences-5th-edition-mendenhall-solutions-manual/
https://testbankdeal.com/product/probability-and-statistics-for-
engineering-and-the-sciences-9th-edition-devore-solutions-manual/
https://testbankdeal.com/product/probability-and-statistics-for-
engineering-and-the-sciences-8th-edition-devore-solutions-manual/
https://testbankdeal.com/product/statistics-for-the-life-sciences-5th-
edition-samuels-solutions-manual/
https://testbankdeal.com/product/organization-theory-and-design-
canadian-2nd-edition-daft-test-bank/
Personal Finance 4th Edition Madura Solutions Manual
https://testbankdeal.com/product/personal-finance-4th-edition-madura-
solutions-manual/
https://testbankdeal.com/product/human-resource-management-11th-
edition-hollenbeck-test-bank/
https://testbankdeal.com/product/p-o-w-e-r-learning-and-your-life-
essentials-of-student-success-3rd-edition-feldman-test-bank/
https://testbankdeal.com/product/applications-and-investigations-in-
earth-science-7th-edition-tarbuck-solutions-manual/
https://testbankdeal.com/product/psychology-an-exploration-
canadian-1st-edition-ciccarelli-test-bank/
Framework for Marketing Management 5th Edition Kotler Test
Bank
https://testbankdeal.com/product/framework-for-marketing-
management-5th-edition-kotler-test-bank/
CHAPTER 10
…………………………………………………………..
Simple Linear Regression
10.2 a. b.
y = 2 + 2x y=4+x
c. d.
y = −2 + 4x y = −4 − x
S 0
140
R-Sq 100.0%
R-Sq(adj) 100.0%
120
100
80
y
60
40
20
0
0 5 10 15 20
x
c. β̂1 = 6.21: For each unit increase in redshift level, the mean value of magnitude
is estimated to increase by 6.21.
10.6 a.
∑ x = 120 ∑x 2
= 1240
∑ y = .37 ∑y 2
= .0127 ∑ xy = 3.86
(∑ x)
2
(120) 2
SS xx = ∑x 2
−
n
= 1240 −
15
= 280
∑ xy − ∑ n∑ = 3.86 − 15 = .9
x y 120(.37)
SS xy =
x=
∑ x = 120 = 8 y=
∑ y = .37 = .0247
n 15 n 15
SSxy .9
βˆ1 = = = .00321
SS xx 280
yˆ = −.00105 + .00321x
216 Chapter 10
d. βˆ0 = −.00105 : We estimate the mean congestion time to be −.00105 minutes when
the number of vehicles is 0.
βˆ1 = .00321 : We estimate the mean congestion time will increase .00321 minutes
for every additional vehicle.
4
Mass
0
0 10 20 30 40 50 60 70
Time
b. Excel was used to fit the simple linear regression model to the data and the results
appear here:
Regression Statistics
Multiple R 0.92376344
R Square 0.853338893
Adjusted R Square 0.846355031
Standard Error 0.857257302
Observations 23
ANOVA
df SS MS F Significance F
Regression 1 89.79419524 89.79419524 122.1872461 3.25999E-10
Residual 21 15.43269171 0.734890082
Total 22 105.226887
βˆ1 = −.114: For each additional one minute in spill time, we estimate the mass of
spill to decrease by .114 pounds.
∑x i = 6167 ∑ y = 135.8
i n = 24
∑x 2
i = 1,641,115 ∑x y
i i = 34765
( ∑ x )( ∑ y )
∑x y −
i i
SSxy = i i
n
(6167)(135.8)
= 34765 − = −129.94167
24
(∑ x )
2
∑
i
SSxx = xi2 −
n
(6167) 2
= 1,641,115 − = 56452.958
24
b. βˆ0 = 6.25: Since x = 0 is not in the observed range, β̂ 0 has no interpretation other
than being the y-intercept.
βˆ1 = −.0023: For each additional increase of 1 part per million of pectin, the mean
sweetness index is estimated to decrease by .0023.
218 Chapter 10
10.12 a. Some preliminary calculations are:
∑ x = 45.12 ∑ y = 114.6
∑x 2
= 88.7788 ∑y 2
= 575.02 ∑ xy = 225.04
(∑ x )
2
(45.12) 2
∑
i
SS xx = xi2 − = 88.7788 − = 3.9532
n 24
∑ xy − ∑ n∑ = 225.04 −
x y (45.12)(114.6)
SS xy = = 9.592
24
x=
∑ x = 45.12 = 1.88 y=
∑ y = 114.6 = 4.775
n 24 n 24
SSxy 9.592
βˆ1 = = = 2.4264
SSxx 3.9532
b.
c. βˆ0 = .2134: When the unflooded area ratio is 0, we estimate the heat transfer
enhancement to be .2134. Note: this value falls outside the range of
our data, and the interpretation is not useful.
βˆ1 = 2.4264: For every 1-unit increase in the unflooded area ratio, we estimate the
heat transfer enhancement to increase by 2.4264 units.
∑x =∑y
nβˆ0 + βˆ1 i i
βˆ ∑ x + βˆ ∑ x = ∑ x y
0 i 1
2
i i i
βˆ0 + βˆ1 x = y
⇒ βˆ0 = y − βˆ1 x
( y − βˆ x ) ∑ x + βˆ ∑ x =∑ x y
1 i 1
2
i i i
⎛
⇒⎜
∑y i
− βˆ1
∑ x ⎞⎟ ∑ x + βˆ ∑ x =∑ x y
i 2
⎜ n n ⎟
i 1 i i i
⎝ ⎠
(∑ x )
2
⇒
∑x ∑y i i
− βˆ 1
i
+ βˆ1 ∑x = ∑x y
2
i i i
n n
⎛
(∑ x ) ⎞
2
∑ x y − ∑n
xi yi
⇒ βˆ1 ⎜ ∑ ⎟=
i
xi2 −
⎜⎜ n ⎟⎟ i i
⎝ ⎠
⇒ βˆ1SS xx = SSxy
SSxy
⇒ βˆ1 =
SSxx
220 Chapter 10
10.18 ( )
Show that E βˆ0 = β 0
( ) ( )
E βˆ0 = E y − βˆ1 x = E ( y ) − β1 x (from Exercise 10.17)
( ∑ y ) − β ∑n ∑x ∑ x ) − β ∑n
x x
=
1
n
E i 1
i
=
1
n
∑(β 0 + β1 xi ) − β1
n
i
=
1
n
(nβ 0 + β1 i 1
i
= β0
(∑ y)
2
.37
SS yy = ∑y 2
−
n
= .0127 −
15
= .0035733
SSE .0006843
s2 = = = .0000526
n−2 15 − 2
s = s 2 = .0000526 = .0072
We expect most of the observed congestion times to fall within +2s = .0144 minutes of
their least squares prediction equation.
∑y ∑ y = 97.8
2
= 1710.2,
(∑ y)
2
( 97.8 )2 = 116.06
SS yy = ∑ y 2
−
n
= 1710.2 −
6
SSE 41.46553
s2 = = = 10.366 s = s 2 = 10.366 = 3.220
n−2 6−2
We expect most of the apparent porosity percentages for bricks to fall within +2s =
6.44% of their least squares predicted values.
∑y ∑ y = 60.1
2
= 262.27,
(∑ y)
2
( 60.1)
2
SS yy = ∑y 2
−
n
= 262.27 −
23
= 105.226
SSE 15.450
s2 = = = .7357 s = s 2 = .7357 = .857
n − 2 23 − 2
We expect most of the mass values to fall within +2s = 1.714 pounds of their least
squares predicted values.
∑y ∑ y = 45.5
2
= 214.41,
(∑ y)
2
( 45.5)2 = 76.393
SS yy = ∑ y 2
−
n
= 214.41 −
15
SSE 18.433
s2 = = = 1.4161 s = s 2 = 1.4161 = 1.190
n − 2 15 − 2
We expect most of the rain gauge amounts to fall within +2s = 2.380 millimeters of
their least squares predicted values.
∑y ∑ y = 135.8
2
= 769.72,
(∑ y)
2
(135.8)2 = 1.318333
SS yy = ∑ y 2
−
n
= 769.72 −
24
SSE 1.0192
s2 = = = .046225 s = s 2 = .046225 = .215
n − 2 24 − 2
We expect most of the sweetness index values to fall within +2s = 0.430 of their least
squares predicted values.
222 Chapter 10
f. From Exercise 10.11,
∑ y = 130.27, ∑ y 2
= 1,081.3975, βˆ1 = .01439, and SSxy = 3640.46471
(∑ y)
2
(130.27) 2
SS yy = ∑ y2 −
n
= 1,081.3975 −
17
= 83.146153
SSE 30.7679
s2 = = = 2.0512
n−2 17 − 2
s = s 2 = 2.0512 = 1.4322
We expect most of the observed times to drill to fall within + 2s = 2.8644 minutes of
their least squares prediction equation.)
∑y
2
= 575.02
(∑ y)
2
(114.6) 2
SS yy = ∑ y2 −
n
= 575.02 −
24
= 27.805
SSE 4.531
s2 = = = .206 s = s 2 = .206 = .4538
n − 2 24 − 2
We expect most of the observed heat transfer enhancement values to fall within ±2s =
.9076 of their least squares predicted value.
∑ y = 40.6022
(∑ y)
2
(16.3) 2
SS = ∑ y −
yy
2
= 40.6022 − = 2.6465
n 7
SSE .2513
s2 = = = .0503 s = s 2 = .0503 = .2242
n−2 7−2
We expect most of the observed shear strength values to fall within ±2s = .4484 of
their least squares predicted value.
∑ x = 5.45 ∑x
2
= 5.5075
∑ y = 239 ∑y ∑ xy = 237.10
2
= 10,255
(∑ x)
2
(5.45) 2
SS xx = ∑x 2
−
n
= 5.5075 −
6
= 0.5570833
x=
∑ x = 5.45 = 0.908333 y=
∑ y = 239 = 39.83333
n 6 n 6
SSxy 20.008333
βˆ1 = = = 35.9162
SS xx 0.5570833
yˆ = 7.2094 + 35.9162 x
(∑ y)
2
( 239 )
2
b. SS yy = ∑y 2
−
n
= 10, 255 −
6
= 734.8333
SSE 16.210
s2 = = = 4.0525 s = s 2 = 4.0525 = 2.013
n−2 6−2
c. We expect most of the drug release rates to fall within +2s = 4.026 of their least squares
predicted values.
(n − 2) s 2
χ2 =
σ2
⎡ (n − 2) s 2 ⎤
( )
V χ2 = V ⎢ ⎥ = 2v = 2(n − 2)
⎣ σ
2
⎦
( n − 2) 2 2σ 4
⇒ V ( s 2 ) = 2(n − 2) = V ( s 2 ) =
σ4 (n − 2)
224 Chapter 10
10.26 a. The 95% confidence interval for β1 is:
βˆ1 ± tα 2 s SSxx
For confidence coefficient .95, α = 1 − .95 = .05 and α/2 = .05/2 = .025. From Table 7
in Appendix B, with df = n − 2 = 6 – 2 = 4, t.025 = 2.776. The 95% prediction interval
is:
For every one millimeter increase in the mean pore diameter of a brick, we are 95%
confident that the apparent porosity of the brick will do anything from decrease by
.00338% to increase by 1.9668%.
H 0 : β1 = 0
H a : β1 ≠ 0
βˆ1 0.9665
The test statistic is t = = = 2.682
s SSxx 3.220 79.8533
For a two tailed test, the rejection region requires α/2 = .05/2 = .025 in both tails of the
t distribution with df = n − 2 = 6 – 2 = 4. From Table 7 in Appendix B, t.025 = 2.776.
The rejection region is t > 2.776 or t < −2.776.
Since the observed value of the test statistic does not fall in the rejection region (t = 2.682
>/ 2.776), H0 cannot be rejected. There is insufficient evidence to indicate that mean pore
diameter and apparent porosity of a brick are linearly related at α = .10.
c. Both the confidence interval and the test of hypothesis fail to conclude that the slope of
the line differs from 0. Therefore, neither indicates that the straight-line model is
useful in predicting the apparent porosity percentage of a brick.
To determine if the rain gauge amount and artificial neural network rain amount are
positively linearly related, we test:
H0: β1 = 0
Ha: β1 > 0
The rejection region requires α = .10 in the upper tail of the t distribution with df =
n – 2 = 15 – 2 = 13. From Table 7, Appendix B, t.10 = 1.350. The rejection region
is t > 1.350.
Since the observed value of the test statistic falls in the rejection region
(t = 10.050 > 1.350), H0 is rejected. There is sufficient evidence to indicate the rain
gauge amount and artificial neural network rain amount are positively linearly related
at α = .10.
b. For confidence coefficient .90, α = 1 − .90 = .10 and α/2 = .10/2 = .05. From Table 7,
Appendix B, with df = n – 2 = 15 – 2 = 13, t.05 = 1.771. The 90% confidence interval is:
s .8187
βˆ1 ± t.05 sβˆ ⇒ βˆ1 ± t.05 ⇒ 1.022 ± 1.771
1
SS xx 64.817333
⇒ 1.022 ± .180 ⇒ (.842, 1.202)
We are 90% confident that the change in the mean value of rain gauge amount for each
unit change in neural network rain is between .842 and 1.202.
10.30 From Exercise 10.12, βˆ1 = 2.4264 and SSxx = 3.9532 . From Exercise 10.20 c, s = .454
s
The confidence interval for β1 is βˆ1 ± tα / 2 sβˆ where sβˆ =
1 1
SSxx
For confidence coefficient .95, α = 1 − .95 = .05 and α/2 = .05/2 = .025. From Table 7 with
df = n − 2 = 24 − 2 = 22, t.025 = 2.074. The 95% confidence interval is:
.454
2.4264 ± 2.074 ⇒ 2.4264 ± .4736 ⇒ (1.9528, 2.9000)
3.9532
We are 95% confident the mean heat transfer enhancement will increase from between
1.9528 and 2.9000 for each 1 unit increase in unflooded area ratio.
10.32 a.
226 Chapter 10
b. Some preliminary calculations are:
∑ x = 2,053 ∑x 2
= 602, 265.5
∑ y = 59.2 ∑y 2
= 517.22 ∑ xy = 17,326.7
(∑ x)
2
(2,053) 2
SS xx = ∑x 2
−
n
= 602, 265.5 −
7
= 149.92857
∑ xy − ∑ n∑ = 17,326.7 −
x y (2,053)(59.2)
SS xy = = −35.814286
7
x=
∑ x = 2,053 = 293.28571 y=
∑ y = 59.2 = 8.4571429
n 7 n 7
SSxy −35.814286
βˆ1 = = = −.2388757 ≈ −.239
SS xx 149.92857
H 0 : β1 = 0
H a : β1 ≠ 0
βˆ1 − 0 −.239 − 0
The test statistic is t = = = −2.31
s / SSxx 1.265 / 149.9286
The rejection region requires α/2 = .01/2 = .005 in both tails of the t distribution with df
= n − 2 = 7 − 2 = 5. From Table 7, Appendix B, t.005 = 4.032. The rejection region is t
> 4.032 or t < −4.032.
Since the observed value of the test statistic does not fall in the rejection region (t =
−2.31 </ −4.032), H 0 is not rejected. There is insufficient evidence to indicate that
temperature is a useful linear predictor of change in free energy.
If we take βˆ1 and subtract its mean and divide by its standard deviation, we will form a
normally distributed random variable with mean 0 and standard deviation 1.
⎡ βˆ − β ⎤
P ⎢ −tα / 2 < 1 1 < tα / 2 ⎥ = 1 − α
⎣⎢ s / SSxx ⎦⎥
⎡ s s ⎤
P ⎢ −tα / 2 < βˆ1 − β1 < tα / 2 ⎥ = 1−α
⎢⎣ SSxx SSxx ⎥⎦
⎡ s s ⎤
P ⎢ − βˆ1 − tα / 2 < − β1 < − βˆ1 + tα / 2 ⎥ = 1−α
⎢⎣ SSxx SSxx ⎥⎦
⎡ s s ⎤
P ⎢ βˆ1 − tα / 2 < β1 < βˆ1 + tα / 2 ⎥ = 1−α
⎣⎢ SSxx SSxx ⎥⎦
10.38 a. βˆ0 = 175.4: We estimate the mean time required to perform the task to equal
175.4 milliseconds when the Index of Difficulty is 0.
βˆ1 = 132.2: For every one unit increase in the Index of Difficulty, we estimate
the mean time to perform the task to increase 133.2 milliseconds.
b. r = .951: There is a strong positive linear relationship between the Index of
Difficulty and the time required to perform the task.
c. To determine if the Index of Difficulty is a useful linear predictor of time, we test:
H 0: ρ = 0
Ha: ρ ≠ 0
The p-value for this is 2 P (t > 38.662) where t is based on df = n − 2 = 160 − 2 = 158.
From Table 7, Appendix B, p < .01.
Using α = .05 (α > p), we can reject H 0 . There is sufficient evidence to indicate the
Fitt’s Law Model is statistically adequate for predicting performance time.
228 Chapter 10
d. r 2 = (.951) 2 = .9044
90.44% of the sum of squares of deviation of the sample time values about their mean
can be explained by using the Index of Difficulty as a linear predictor.
10.40 Radiata Pine: 84% of the variation in the sample stress values around their mean can be
explained by the linear relationship with the natural logarithm of number
of blade cycles.
Hoop Pine: 90% of the variation in the sample stress values around their mean can be
explained by the linear relationship with the natural logarithm of number of
blade cycles.
10.42 a. There is a strong negative linear relationship between number of online courses and
weekly quiz grade.
H 0: ρ = 0
Ha: ρ < 0
r n−2 −.726 24 − 2
The test statistic is t = = = −4.952
1− r2 1 − (−.726) 2
For a one tailed test, the rejection region requires α = .05 in the lower tail of the t
distribution with df = n − 2 = 24 – 2 = 22. From Table 7 in Appendix B, t.05 =
1.717. The rejection region is t < −1.717.
Since the observed value of the test statistic does fall in the rejection region (t = −4.952 <
−1.717), H 0 can be rejected. There is sufficient evidence to indicate that a significant
negative correlation exists between number of online courses and weekly quiz grade.
10.44 a. βˆ1 = 450: For each additional processing step required, we estimate the mean
response time to increase 450 milliseconds.
b. r 2 = .91: 91% of the sum of squares of deviations of the sample response times
about their means can be explained by using the number of processing
steps required as a linear predictor.
c. H 0: ρ = 0
Ha: ρ ≠ 0
r n−2 .954 8 − 2
The test statistic is t = = = 7.79
1− r 2 1 − .91
testbankdeal.com