Beruflich Dokumente
Kultur Dokumente
1) Calculated Chi Square = 7.286535, Critical Chi Square at 1% level and 6 d.f. = 16.812;
Accept H0. The percentage distribution of the U.S. labor force by education attainment
has not changed since 1992.
2) H0: Given data follows Poisson distribution.
H0: Given data does not follow Poisson distribution.
= =1.94
1.94
X
f0
P(X=x)=
(1.94) fe=150*P(X=x)
!
0
1
2
3
4
5
Total
2 =
21
37
44
30
14
4
150
(0 ) 2
0.1437
0.2788
0.2704
0.1749
0.0848
0.0474
1
21.556
41.818
40.563
26.231
12.722
7.110
150
(0 ) 2
0.014
0.555
0.291
0.542
0.128
1.361
2.891
= 2.891
From the tables of 2 distribution with 6-1-1= 4 d.f. we have the critical value of
9.49 at 5% level of significance. Since 2 < 9.49 we cannot reject the null
hypothesis and conclude that the given data follows Poisson distribution.
3) Calculated Chi Square = 0.86482, Critical Chi Square at 2.5% level and 2 d.f. = 7.378;
Accept H0. The credit card holders in this state are not different from all credit card
holders with respect to making payments on their credit card bills.
4) Calculated Chi Square = 6.75, Critical Chi Square at 5% level and 4 d.f. = 9.488; Accept
H0. The null hypothesis that the orders are evenly distributed over the days of the
week is true.
5) After Pooling
Calculated Chi Square = 10.96. Test of Goodness of fit is considered as a right tailed
test. So p-value = P(2(7) > 10.96) = 1- 0.859627 =0.140373. Fix level of significance at
5%. H0: Data follows Poisson, H1: Data does not follow Poisson. Since p-value > 0.05,
we accept H0 at 5% level.
6) Calculated Chi Square = 10.11719, Critical Chi Square at 5% level and 5 d.f. = 11.0705;
Accept H0. The observed distribution of X may be defined by the probability () =
(1 )1, where p =1/2.
7) Calculated Chi Square = 19.5833, Critical Chi Square at 5% level and 2 d.f. = 5.991465;
Reject H0. Data is not consistent with the companys claim.
8)
Observed Frequencies
Employed
Unemployed
Male
1480
5720
Female
120
680
Total
1600
6400
Total
7200
800
8000
Calculated Chi Square = 13.8889, Critical Chi Square at 5% level and 1 d.f. = 3.8415;
Reject H0. We conclude that distinction is made in appointment on the basis of sex.
9) Calculated Chi Square = 128.448, Critical Chi Square at 5% level and 2 d.f. = 5.991465;
Reject H0. Three media sources do not have the same promotional impact on
customers.
10) Calculated Chi Square = 68.66277, Critical Chi Square at 5% level and 3 d.f. = 7.814728;
Reject H0. The percentage distribution of the opinions of the users of the redesigned
product is different from the percentage distribution of the users of this product
before it was redesigned.
11)
(a)
Source of Variation
Sum of D.F.
Squares
Mean Sum F
F Critical
of Squares Calculated ( = 0.05)
1
13172.02
1.419351 4.01954
2
49419.32
5.32518 3.16825
2
804.8167
0.086723 3.16825
SS
df
MS
P-value
F crit
Between Groups
Within Groups
0.520833
31.86833
1
10
Total
32.38917
11
0.520833 0.163433
3.186833
0.694526
4.964603
(b) Two types of shock absorbers are not significantly different in mean strength at 5%
level of significance level.
(c)
t-Test: Two-Sample Assuming Equal Variances
Mean
Variance
Observations
Pooled Variance
Hypothesized
Mean Difference
df
t Stat
t Critical two-tail
(5%)
Manufacturer
10.71667
3.069667
6
3.186833
Competitor
10.3
3.304
6
0
10
0.404268
2.228139
Sum of Squares
SALES_TECHNIQUE
STORE_SIZE
Mean Square
Sig.
23.333
7.778 6.512
.026
136.167
68.083 57.000
.000
7.167
166.667
11
Error
Corrected Total
df
Reject H0 at 5%
1.194
-2.6667
Accept H0 of No Difference.
15)
Std. Error
.89235
Sig.
Lower Bound
.118
-6.0377
Upper Bound
.7044
Source
Sum of Squares
INTERACTION
df
Mean Square
Sig.
At 5%
16.680
2.780
2.393
.093
NO DIFFERENCE
5.333
2.667
2.296
.143
NO DIFFERENCE
GASOLINE_ADD
85.280
28.427
24.471
.000
DIFFERENT
Error
13.940
12
1.162
Total
121.233
23
CAR
16)
a)
b) 3.1884
17)
a)
b) 67.39
18)
The regression equation is
Y=8.103 + 7.602 X1 + 3.111 X2
Predictor
Constant
X1
X2
S=3.335
Coef
8.103
7.602
3.111
R-sq = 92.3%
SE Coef
2.667
2.105
0.613
R-sq (adj) =
T
3.038245
3.611401
5.075041
91.02%
19) The admissions officer for Clearwater College developed the following estimated regression
equation relating final college GPA to the students SAT mathematics score and high-school
GPA.
= - 1.41+ .0235x1 + .00486x2, where x1 = high-school grade point average, x2 = SAT
mathematics score, y = Final college grade point average. A portion of the Minitab
computer output follows:
Coef
-1.4053
0.023467
0.00486
SE Coef
0.4848
0.008666
0.001077
S=0.1298
R-sq = 93.73%
R-sq (adj) =
T
-2.89872
2.707939
4.512535
91.94%
20) The personnel director for Electronics Associates developed the following estimated
regression equation relating an employees score on a njob satisfaction test to length of
service and wage rate.
= - 14.4- 8.69x1 + 13.5x2, where x1 = length of service (year), x2 = wage rate (dollars), y =
job satisfaction test score (higher scores indicate greater job satisfaction). A portion of the
Minitab computer output follows:
The regression equation is
Y= 14.4 8.69 X1 +13.52 X2
Predictor
Constant
X1
X2
S=3.733
Coef
14.448
-8.69
13.517
R-sq =90.12%
SE Coef
8.191
1.555
2.085
R-sq (adj)=
T
1.76
-5.58842
6.482974
86.16%
21)
a) Score = = 50.6095 + 1.5621 RecRes. The H0 of F test rejected at the .05 level of
significance. Linear model is valid.
b) R-Sq = 0.43, Adj R-Sq = 0.40. Model is not good enough.
c) Score = = 33.4848 + 1.8998 RecRes + 2.6108 Afford. The H0 of F test rejected at
the .05 level of significance. Linear model is valid. R-Sq = 0.81, Adj R-Sq = 0.78.
Model is improved and good enough.
22)
a) Speed = 97.570 + 0.069 Price + 0.000 Curb_Weight + 0.059 Horsepower 2.484
zero_to_60.
b) Using the F test, we determine that the linear model is valid.
c) At 10% level of significance, Curb_Weight is insignificant, all other regressors are
significant. At 5% level of significance, Curb_Weight and Price are insignificant
d) Speed = 95.384 + 0.073 Price + 0.057 Horsepower 2.474 zero_to_60.
Notice that the values of coefficients do not change much.
23)
a) CityMPG = 24.121 2.102 Displacement. All H0 under t test and F test are rejected
at 5% level of significance. Model is valid. R-Sq and Adj R-Sq are very small.
b) CityMPG = 26.383 2.439 Displacement -1.201 Drive4. All H0 under t test and F
test are rejected at 5% level of significance. Model is valid. R-Sq and Adj R-Sq are
improved a bit.
c) Dummy variable added in part (b) is significant at = .05.
d) CityMPG = 33.333 4.149 Displacement -1.237 Drive4 +2.161 EightCyl. R-Sq and
Adj R-Sq are improved.
e) All H0 under t test and F test are rejected at 5% level of significance. Model is valid.
24) Todays marketplace offers a wide choice to buyers of sport utility vehicles (SUVs) and pickup
trucks. An important factor too many buyers is the resale value of the vehicle. The following
table shows the resale value (%) after two years and the suggested retail price for 10 SUVs, 10
small pickup trucks, and 10 large pickup trucks (Kiplingers New Cars and Trucks 2000 Buyers
Guide).
a) Resale_Value = 0.002Suggested_Price. All H0 under t test and F test are rejected at
5% level of significance. Model is valid. R-Sq and Adj R-Sq are close to 1.
b) Yes. All H0 under t test and F test are rejected at 5% level of significance. Model is
valid. R-Sq and Adj R-Sq are close to 1.
c) Resale_Value = 0.002 Suggested_Price + 2.516 Type. [Type = 0, 1 and 2 for Sport
Utility, Small Pickup and Full-size Pickup respectively.]
d) Adj R-Sq is not improved. F test suggests that model is valid. Using t test, we find that
Type is not significant.
25) A 10-year study conducted by the American Heart Association collected data on how age,
blood pressure, and smoking relate to the risk of strokes. Risk is interpreted as the probability
(times 100) that the patient will have a stroke over the next 10-year period. A linear model is
fitted to predict the Risk of strokes (Risk) using age (Age) and blood pressure (BP). The output
of SPSS is as follows:
Model Summary
Model
R Square
.898a
Adjusted R
Square
.806
Std. Error of
the Estimate
0.783
6.90826
Model
1
Regression
Mean Square
3377.9060
1688.9529
813.0443
17
47.8261
4190.9500
19
220.5763
Residual
Total
df
F
35.3144
B
(Constant)
Std. Error
-110.942
16.470
-6.7360
Age
1.315
.173
7.6012
BP
.296
.051
5.8039
26)
a)
Model
I
II
III
b)
F Statistic
15.64103
20.58104
9.740506
Critical Value
4.964603
4.964603
4.256495
Reject H0
Reject H0
Reject H0
Model
Coefficients
T Statistic
Critical Value
0
1
II
0
2
III
0
1
2
3.399639
3.952562
0.587002
4.537125
0.77078
0.558036
1.455102
2.2281
2.2281
Significant
Significant
2.2281
2.2281
Insignificant
Significant
2.2622
2.2622
2.2622
Insignificant
Insignificant
Insignificant
c) Model II is the best. It has highest Adjusted R-Sq. It could be improved by removing
intercept.
d) Normality is required for the validity of F and t tests.
27) Predicted Y = 3.239 X2 (No intercept model will be better as intercept comes to be
insignificant.) Inclusion of both regressors creates multicollinearity. Regressor X2 is included
as it has higher correlation with Y.
Adj R-Sq=0.903