- Attendance: 10 %

- Student work 20 %
- Individual Assignment 20 % (buổi 6, 7  16 topics, mỗi người 4 – 5 bài)
- Final exam 50 %

Hypothesis testing
S1:
H0 mean x(male) = mean x(female)
H1 mean x(male) ≠ mean x(female)  bigger/ smaller
S2: Method: Independent Samples t-test
S3: Descriptive statistics: N, mean x, s
S4: Assumption of the homogeneity of the variance
Nhóm đồng nhất là nhóm có phương sai của 2 mean không quá khác biệt
Levene’s test: Equal variance
F Levene's test=?
P Levene's test=?, ≤0.05
 P>0.05  Equal variance assumed
 P≤0.05  Equal variance not assumed

S5: Result of t-test

 t =?
 P=?, ≤0.05  H1 supported  bigger/ smaller
 mean difference

 sig(p-value)
Step 1:
H0: There is no difference of the average household income between male and female
H1: There is a significant difference of the average of the average household income
between male and female
Step 2: Methodology
Step 3: Descriptive statistics

Group Statistics

Gender Std. Error

N Mean Std. Deviation Mean

Household income in Female 3179 68.7798 75.73510 1.34323

thousands
Male 3221 70.1608 81.56216 1.43712

Step 4: Assumptions
Independent Samples Test

Levene's Test for

Equality of Variances t-test for Equality of Means

95% Confidence
Interval of the
Difference

Sig. (2- Mean Std. Error

F Sig. t df tailed) Difference Difference Lower Upper

Household income Equal variances 1.865 .172 -.702 6398 .483 -1.38101 1.96808 -5.23912 2.47709
in thousands assumed

Equal variances not -.702 6374.362 .483 -1.38101 1.96713 -5.23725 2.47522
assumed

FLevene’s = 1.865, pLevene’s test = 0.172 > 0.05

 Equal variance assumed
 Step 5: Result
t=-0.702, p=0.483 > 0.05
 There is no difference of the average household income between male and female

---------------------------------------------------------------------------------------------------------
Step 1:
H0: There is no difference of the average household income between wireless and no
wireless service
H1: There is a significant difference of the average of the average household income
between wireless and no wireless service
Step 2: Methodology
Step 3: Descriptive statistics
Description: There are 3853 ppl with wireless internet service, while there are 2547 ppl
without wireless internet service
The answer income for the former group is 6292, while the latter is 7930

Group Statistics

Wireless service Std. Std. Error

N Mean Deviation Mean

Household income in No 3853 62.9735 67.03762 1.07999

thousands dimension1
Yes 2547 79.3098 92.81293 1.83905

Step 4: Assumptions
Independent Samples Test

Levene's Test for

Equality of Variances t-test for Equality of Means

95% Confidence
Interval of the
Difference

Sig. (2- Mean Std. Error

F Sig. t df tailed) Difference Difference Lower Upper

Household income Equal variances 73.179 .000 -8.168 6398 .000 -16.33625 2.00002 -20.25696 -12.41554
in thousands assumed

Equal variances not -7.660 4269.256 .000 -16.33625 2.13272 -20.51749 -12.15501
assumed

FLevene’s = 73.179, pLevene’s test = 0.0001 < 0.05

 Equal variance not assumed

Step 5: Result
t=-7.660, p < 0.0001 < 0.05
 There is a significant difference of the average of the average household income
between wireless and no wireless service (H1 supported)
Income of the ones who use the wireless service is 16336$ higher than the ones who
don’t and it is significant at 0.001 level

PAIRED-SAMPLES T-TEST
Step 1: mean xA = mean xA’
H0 : mean xest = mean xact
H1 : mean xest ≠ mean xact
Step 2: Methodology: Paired sample t-test
Step 3: Descriptive statistics
Step 4: Correlation  r=?

 p=? < 0.05

  How big – Strength – Correlation

Step 5: t-test result

 t=?
 p≤0.05
 Bigger/smaller – mean difference – sig?

Step 1:
H0
H1
Step 2: Methodology
Step 3: Descriptive statistics

Paired Samples Statistics

Std. Error
Mean N Std. Deviation Mean

Pair 1 Estimated 28.1776 311 15.99406 .90694

Actual 34.5562 311 16.34048 .92658

Step 4:

Paired Samples Correlations

N Correlation Sig.

Pair 1 Estimated & Actual 311 .797 .000

The estimated data and actual data have a strong correlation with r=0.797 and it is
significant at 0.001 level
Step 5: Result
Paired Samples Test

Paired Differences

95% Confidence Interval of the

Difference

Std.
Mean Deviation Std. Error Mean Lower Upper t df Sig. (2-tailed)

Pair 1 Estimated - Actual -6.37868 10.30853 .58454 -7.52886 -5.22851 -10.912 310 .000

t=-10.912, p<0.001
 H1 is supported
 There is a significant difference between the estimated data and actual data
 The estimated data is smaller than the actual data and the mean difference is 6.379
and it is significant at 0.001 level

ANOVA n0 group ≥ 2
Step 1:
H0 = mean xA = mean xB = …= mean xi
H1 = at least 1 difference (e.g mean xA ≠ mean xB= mean xc)
Step 2: Method ANOVA
Step 3: Descriptive statistics
Step 4: Assumptions of the homogeneity of variance
FLevene’s =?; PLevene’s test=?  PLevene’s > 0.05  equal variance asssumed

 PLevene's ≤ 0.05  equal variance not assumed

Step 5: Result of ANOVA

- Equal variance assumed  ANOVA table  F=?

 P ≤ 0.05?

 H1 supported
 - Equal variance not assumed  ANOVA table: the result could be wrong
 Robust test (Welch/ Brown F…); FWelch=?; P ≤ 0.05
 H1 supported

Step 1:
H0: There is no significant difference in the average household income among groups
who drive different types of cars.
H1= There is a significant difference in the average household income among groups who
drive different types of cars.
Step 2: Methodology: ANOVA
Step 3: Descriptive statistics

Descriptives

Household income in thousands

95% Confidence
Interval for Mean

Std. Std. Lower Upper

N Mean Deviation Error Bound Bound MinimumMaximum

Economy 1841 21.8876 5.24123 .12215 21.6480 22.1271 9.00 31.00

Standard 2275 42.5600 8.56966 .17967 42.2077 42.9123 29.00 61.00

Luxury 2284 134.6410102.35556 2.14172130.4411 138.8409 58.00 1116.00

Total 6400 69.4748 78.71856 .98398 67.5459 71.4038 9.00 1116.00

Make the interpretation with smallest/biggest number and Std.

Step 4: Homogeneity of variance test

Test of Homogeneity of Variances

Household income in thousands

Levene Statistic df1 df2 Sig.

1129.720 2 6397 .000

FLevene’s test = 1129.720

pLevene’s test < 0.001
 Equal variance not assumed

Step 5: Result

ANOVA

Household income in thousands

Sum of Squares df Mean Square F Sig.

Between Groups 1.552E7 2 7758179.030 2056.246 .000

Within Groups 2.414E7 6397 3772.982

Total 3.965E7 6399

Because the Levene test is significant, we use the Robust test of equality of the means
Robust Tests of Equality of Means

Household income in thousands

Statistica df1 df2 Sig.

Welch 5752.869 2 3825.901 .000

a. Asymptotically F distributed.

FWelch = 5752.87, pWelch < 0.001

 There is at least one significant difference in the average household income among
groups who drive different types of cars.
Step 6: Post-hoc test
Use LSP, Tukey, Ducan  compare pairs (p-value)

Use T2, T3, Games-Howell  compare pairs (p-value)

Multiple Comparisons

Household income in thousands

Tamhane; I-J = Mean difference

(I) Primary vehicle (J) Primary vehicle 95% Confidence

price category price category Interval
Mean
Difference (I- Std. Lower Upper
J) Error Sig. Bound Bound

Economy Standard -20.67244* .21726 .000 -21.1914 -20.1534

Luxury -112.75342* 2.14520.000 - -

117.8793 107.6275

Standard Economy20.67244* .21726 .000 20.1534 21.1914

dimension2
Luxury -92.08098* 2.14925.000 -97.2165 -86.9454

Luxury Economy112.75342* 2.14520.000 107.6275 117.8793

Standard 92.08098* 2.14925.000 86.9454 97.2165

*. The mean difference is significant at the 0.05 level.

The average household income of the people who drive the economy car is 2067244$ and
112753$ lower compared to the people who drive the standard and luxury car,
respectively. The mean differences are significant at 0.001 level.
3 groups  3 comparisons
4 groups  6
5 groups  10
C52
Step 1:
H0: There is no significant difference in the average household income among groups
who have different education backgrounds.
H1= There is a significant difference in the average household income among groups who
have different education backgrounds.
Step 2: Methodology: ANOVA
Step 3: Descriptive statistics

Descriptives

Household income in thousands

95% Confidence
Interval for Mean

Std. Std. Lower Upper

N Mean Deviation Error Bound Bound MinimumMaximum

Did not 1390 59.866261.30036 1.6442056.6408 63.0916 9.00 558.00

complete high
school

High school 1936 66.207172.72591 1.6528662.9656 69.4487 9.00 837.00

degree

Some college 1360 70.134681.03878 2.1974765.8238 74.4454 9.00 1070.00

College degree 1355 78.650292.87753 2.5231473.7005 83.5999 9.00 1116.00

Post- 359 87.169994.79998 5.0033577.3303 97.0096 9.00 1045.00

undergraduate
degree

Total 6400 69.474878.71856 .98398 67.5459 71.4038 9.00 1116.00

Make the interpretation with smallest/biggest number and Std.
The biggest group of people belongs to the people with a highschool degree at 1936
people, while people with post-undergraduate degrees accounts for the least number at
only 359 people. The highest Standard deviation belongs to the Post-undergraduate
degree group, while the people who did not finish highschool takes up the smallest
Standard deviation.
Step 4: Homogeneity of variance test

Test of Homogeneity of Variances

Household income in thousands

Levene
Statistic df1 df2 Sig.

14.766 4 6395 .000

FLevene’s test = 14.766

pLevene’s test < 0.001
 Equal variance not assumed

Step 5: Result of ANOVA test

ANOVA

Household income in thousands

Sum of Squares df Mean Square F Sig.

Between Groups 376079.699 4 94019.925 15.309 .000

Within Groups 3.928E7 6395 6141.680

Total 3.965E7 6399

Significant at 0.001 level
Because the Levene test is significant, we use the Robust test of equality of the means

Robust Tests of Equality of Means

Household income in thousands

Statistica df1 df2 Sig.

Welch 14.622 4 1900.426 .000

a. Asymptotically F distributed.

FWelch = 14.622, pWelch < 0.001

 There is at least one significant difference in the average household income among
groups who have different educational backgrounds.
Step 6: Post-hoc test

Multiple Comparisons
Household income in thousands
Tamhane

(I) Level of (J) Level of 95% Confidence

education education Interval
Mean
Difference Std. Lower Upper
(I-J) Error Sig. Bound Bound

Did not complete High school degree-6.34094 2.33139 .064 -12.8724 .1905
high school
Some college -10.26837* 2.74450 .002 -17.9587 -2.5781

College degree -18.78400* 3.01158 .000 -27.2233 -10.3447

Post-undergraduate -27.30373* 5.26659 .000 -42.1229 -12.4846

degree
High school degreeDid not complete 6.34094 2.33139 .064 -.1905 12.8724
high school
Some college -3.92743 2.74970 .811 -11.6318 3.7769
College degree -12.44306* 3.01632 .000 -20.8952 -3.9909
Post-undergraduate -20.96279* 5.26930 .001 -35.7894 -6.1362
degree
Some college Did not complete 10.26837* 2.74450 .002 2.5781 17.9587
high school
High school degree3.92743 2.74970 .811 -3.7769 11.6318
College degree -8.51563 3.34591 .105 -17.8907 .8594
Post-undergraduate -17.03536* 5.46465 .019 -32.4016 -1.6691
degree
College degree Did not complete 18.78400* 3.01158 .000 10.3447 27.2233
high school
High school degree12.44306* 3.01632 .000 3.9909 20.8952
Some college 8.51563 3.34591 .105 -.8594 17.8907
Post-undergraduate -8.51973 5.60355 .749 -24.2704 7.2309
degree
Post-undergraduate Did not complete 27.30373* 5.26659 .000 12.4846 42.1229
degree high school

High school degree20.96279* 5.26930 .001 6.1362 35.7894

Some college 17.03536* 5.46465 .019 1.6691 32.4016

College degree 8.51973 5.60355 .749 -7.2309 24.2704

*. The mean difference is significant at the 0.05 level.

The average household income of the people who did not finish highschool is $634094,
$1026837, $1878400, $2730373 lower compared to people who have highschool degree,
some college, college degree and post-undergraduate degree, respectively.
The average household income of the people who have highschool degree is $392743,
$1244306, $2096279 lower compared to people who went to some college, had college
degree and post-undergraduate degree, respectively.
The average household income of the people who went to some college is $851563,
$1703536 lower compared to people who had college degree and post-undergraduate
degree, respectively.
The average household income of the people who had college degree is $851973 lower
compared to people who had post-undergraduate degree.
The mean difference is significant at 0.001 level.

17. Using the Excel file Facebook Survey, determine if the mean number of hours
spent online per week is the same for males as it is for females.
Step 1:
H0: There is no difference of the average number of hours spent online per week between
males and females
H1: There is difference of the average number of hours spent online per week between
males and females
Step 2: Methodology: Independent – Sample T-Test
Step 3: Descriptive statistics
T-Test
[DataSet1]
Group Statistics

Gender Std. Error

N Mean Std. Deviation Mean

Hours online/week female 20 6.15 3.167 .708

dimension1
male 13 6.38 3.203 .888

- There are 20 females joined in the test with the average online hours per week of
6.15 hours, Std is 3.167
- There are 13 males joined in the test with the average online hours per week of
6.38 hours, Std is 3.203
Step 4: Assumptions
Independent Samples Test

Levene's Test
for Equality
of Variances t-test for Equality of Means

95%
Confidence
Interval of
the
Sig. Difference
(2- Mean Std. Error
F Sig. t df tailed) Difference Difference LowerUpper

Hours Equal .240 .628 -.20 31 .837 -.235 1.133 -2.546 2.077
online/week variances 7
assumed
Group Statistics

Gender Std. Error

N Mean Std. Deviation Mean

Hours online/week dimension1female 20 6.15 3.167 .708

Equal -.20 25.576.838 -.235 1.136 -2.571 2.102

variances 7
not
assumed

FLevene’s = 0.240, pLevene’s test = 0.628 > 0.005  Equal variance assumed

Step 5: Result
t=-0.207, p = 0.837 > 0.05
 There is no difference of the average number of hours spent online per week
between males and females (H1 not supported). In particular, the average hours of
online per week of females is 0.235 hour higher than males.
20. In the Excel file Cell Phone Survey, test the hypothesis that the mean responses
for Value for the Dollar and Customer Service do not differ by gender.
Step 1:
H0: There is no difference of average responses for Value for the Dollar and Customer
Service between males and females
H1: There is difference of average responses for Value for the Dollar and Customer
Service between males and females
Step 2: Methodology: Independent – Sample T-Test
Step 3: Descriptive statistics
T-Test
[DataSet1]
Group Statistics

Gender Std. Error

N Mean Std. Deviation Mean

Value for the Dollar F 18 3.39 .979 .231

dimension1
M 34 3.44 .960 .165

Customer Service F 18 2.94 .873 .206

dimension1
M 34 3.38 .985 .169

- For the Value for the Dollar, there are 18 females joined the test with the mean value of
3.39, Std is 0.979; there are 34 males joined the test with the mean value of 3.44, Std is
0.960.
- For the Customer Service, there are 18 females joined the test with the mean value of
2.94, Std is 0.873; there are 34 males joined the test with the mean value of 3.38, Std is
0.985.
Step 4: Assumptions
Independent Samples Test

Levene's Test
for Equality
of Variances t-test for Equality of Means

95%
Confidence
Interval of
the
Sig. Difference
(2- Mean Std. Error
F Sig. t df tailed) Difference Difference Lower Upper

Value for Equal .020 .889 -.186 50 .853 -.052 .282 -.618 .513
the variances
Dollar assumed

Equal -.185 34.153.855 -.052 .283 -.628 .523

variances
not
assumed

Customer Equal 2.688 .107 - 50 .119 -.438 .276 -.993 .117

Service variances 1.584
assumed

Equal - 38.625.108 -.438 .266 -.976 .101

variances 1.645
not
assumed

- Value for the Dollar: FLevene’s = 0.020, pLevene’s test = 0.889 > 0.005  Equal variance
assumed
- Customer Service: FLevene’s = 2.688, pLevene’s test = 0.107 > 0.005  Equal variance
assumed
Step 5: Result
- Value for the Dollar: t=-0.186, p = 0.853 > 0.05
- Customer Service: t=-1.584, p = 0.119 > 0.05
 There is no difference of average responses for Value for the Dollar and Customer
Service between males and females (H1 not supported). In particular, the average
responses for Value for the Dollar of females is 0.052 higher than of males, while the
average responses for Customer Service of females is 0.438 higher than of males.
22. Determine if there is evidence to conclude that the mean GPA of males who plan
to attend graduate school is larger than that of females who plan to attend graduate
school using the data in the Excel file Graduate School Survey.
Step 1: Hypothesis
H0: The mean GPA of males who plan to attend graduate school is not larger than that of
females who plan to ateen graduate school.
H1: The mean GPA of males who plan to attend graduate school is larger than that of
females who plan to ateen graduate school.
Step 2: Methodology: Independent Sample T-test
Step 3: Descriptive Statistics
T-Test

Group Statistics

Gender Std. Error

N Mean Std. Deviation Mean

Undergraduate GPA F 8 3.613 .3980 .1407

dimension1
M 11 3.336 .4545 .1370

Description: There are 8 females and 11 males plan to attend graduate school. The mean
undergraduate GPA for females is 3.613, Std Deviation is 0.3980, while the mean
undergraduate GPA for males is 3.336, Std Deviation is 0.4545.
Step 4: Assumptions
Independent Samples Test

Levene's
Test for
Equality
of
Variances t-test for Equality of Means

95%
Confidence
Interval of
the
Sig. Difference
(2- Mean Std. Error
F Sig. t df tailed) Difference Difference LowerUpper

Undergraduate Equal .256 .619 1.37517 .187 .2761 .2008 -.1475 .6998
GPA variances
assumed

Equal 1.40616.307.179 .2761 .1964 -.1396 .6919

variances
not
assumed

FLevene’s = 0.256, pLevene’s test = 0.619 > 0.005  Equal variance assumed

Step 5: Result
t = 1.375, p = 0.187 > 0.05
 The mean GPA of males who plan to attend graduate school is not larger than that of
females who plan to ateen graduate school. (H1 not supported). It is significant at 0.001
level.
29. A college is trying to determine if there is a significant difference in the mean
GMAT score of students from different undergraduate backgrounds who apply to
the MBA program. The Excel file GMAT Scores contain data from a sample of
students. What conclusion can be reached using ANOVA?
Step 1: Hypothesis
H0: There is no difference in the mean GMAT score of students from different
undergraduate backgrounds.
H1: There is at least one difference in the mean GMAT score of students from different
undergraduate backgrounds.
Step 2: Methodology: ANOVA
Step 3: Descriptive statistics:

Descriptives

GMAT Scores

95% Confidence
Interval for Mean

Std. Std. Lower Upper

N Mean Deviation Error Bound Bound MinimumMaximum

Business 13 584.08 11.601 3.217 577.07 591.09 565 605

Liberal 7 572.00 7.461 2.820 565.10 578.90 562 584

Arts

Sciences 17 596.06 9.516 2.308 591.17 600.95 580 612

Total 37 587.30 13.412 2.205 582.83 591.77 562 612

Description: Overall, there are 37 students joined the test, with 13 students in Business,
7 students in Liberal Arts and 17 students in Sciences. The average GMAT score of 3
majors is 587.3, with the Std Deviation of 13.412. The average GMAT score of Business
major is 584.08 with the Std Deviation of 11.601. The average GMAT score of Liberal
Arts major is the lowest with 572, Std Deviation is 7.461. Sciences students have the
highest average GMAT score with 596.06, Std Deviation is 9.516.
Step 4: Assumptions of the homogeneity of variance

Test of Homogeneity of Variances

GMAT Scores

Levene Statistic df1 df2 Sig.

1.183 2 35 .318

FLevene’s =1.183; PLevene’s test= 0.318 > 0.05  equal variance asssumed

Step 5: Result of ANOVA

ANOVA

GMAT Scores

Sum of Squares df Mean Square F Sig.

Between Groups 2983.945 2 1491.973 14.948 .000

Within Groups 3493.423 35 99.812

Total 6477.368 37

F= 14.948; P < 0.001 ≤ 0.05

 H1 supported  At least two of the three groups differ significantly with regard to
the average GMAT scores.

30. Using the data in the Excel file Cell Phone Survey, apply ANOVA to determine if
the mean response for Value for the Dollar is the same for different types of cell
phones.
Step 1: Hypothesis
H0: There is no difference between types of cell phones regarding the average response
for Value for the Dollar.
H1: There is at least 1 difference between types of cell phones regarding the average
response for Value for the Dollar.
Step 2: Methodology: ANOVA table
Step 3: Descriptive statistics

Descriptives

Value for the Dollar

95% Confidence
Interval for Mean

Std. Std. Lower Upper

N Mean Deviation Error Bound Bound MinimumMaximum

Smart 21 3.81 1.030 .225 3.34 4.28 2 5

Camera 19 3.16 .958 .220 2.70 3.62 1 5

Basic 12 3.17 .577 .167 2.80 3.53 2 4

Total 52 3.42 .957 .133 3.16 3.69 1 5

Overall, there are 52 people joined the test, with 21 people using Smart cell phones, 19
people using Camera cell phones and 12 people using Basic cell phones. The average
response for Value for the Dollar of 3 types is 3.42, with the Std Deviation of 0.957. The
average response of Smart, Camera and Basic cell phone users are 3.81, 3.16, 3.17, the
Std Deviation is 1.030, 0.958, 0.577, respectively; in which Smart phone users have the
highest average response, while that of Camera cell phone users is the lowest.
Step 4: Assumptions of the homogeneity of variance
Test of Homogeneity of Variances

Value for the Dollar

Levene Statistic df1 df2 Sig.

3.171 2 49 .051

FLevene’s = 3.171, pLevene’s test = 0.051 > 0.005  Equal variance assumed

Step 5: Result of ANOVA

ANOVA

Value for the Dollar

Sum of Squares df Mean Square F Sig.

Between Groups 5.261 2 2.631 3.111 .053

Within Groups 41.431 49 .846

Total 46.692 51

F= 3.111; P = 0.053 > 0.05  H1 not supported

 There is no difference between types of cell phones regarding the average response
for Value for the Dollar.

S1: Model summary

Model Summary

Model Std. Error of the

R R Square Adjusted R Square Estimate

dimension01 .361a .131 .109 $9,961.98403

a. Predictors: (Constant), House Age

S2: ANOVA

ANOVAb

Model Sum of Squares df Mean Square F Sig.

1 Regression 5.964E8 1 5.964E8 6.010 .019a

Residual 3.970E9 40 9.924E7

Total 4.566E9 41

a. Predictors: (Constant), House Age

b. Dependent Variable: Market Value

H0: β = 0  No regression line

H1: At least one β # 0  there is a regression line

S3: Assessment
Coefficientsa

Model Standardized
Unstandardized Coefficients Coefficients

B Std. Error Beta t Sig.

1 (Constant) 45217.761 19172.989 2.358 .023

House Age 1570.434 640.601 .361 2.452 .019

a. Dependent Variable: Market Value

C: t =?, p< 0.05  significant

House age p < 0.05  significant

S4: Regression model with unstandardized coefficient

MV = 45217 + 1570*HA
With standardized coefficient: MV = 0.369*HA

S1: Model summary

Model Summary

Model Std. Error of the

R R Square Adjusted R Square Estimate

dimension01 .388a .151 .151 1.261

a. Predictors: (Constant), Level of education, Household income in thousands, Primary

vehicle price category

S2: ANOVA
ANOVAb

Model Sum of Squares df Mean Square F Sig.

1 Regression 1808.781 3 602.927 378.960 .000a

Residual 10176.059 6396 1.591

Total 11984.840 6399

a. Predictors: (Constant), Level of education, Household income in thousands, Primary

vehicle price category

b. Dependent Variable: Job satisfaction

H0: β = 0  No regression line

H1: At least one β # 0  there is a regression line

S3: Assessment
C: t =?, p< 0.05  significant

House age p < 0.05  significant

Coefficientsa

Model Unstandardized Standardized Collinearity

Coefficients Coefficients Statistics

B Std. ErrorBeta t Sig. ToleranceVIF

1 (Constant) 2.415 .055 44.210 .000

Household .003 .000 .150 10.534 .000 .655 1.528

income in
thousands

Primary vehicle .452 .024 .264 18.540 .000 .653 1.532

price category

Level of -.184 .013 -.161 - .000 .987 1.014

education 13.858

a. Dependent Variable: Job satisfaction

LMS

Indp Model 1 Model 2 Model 3 Model 4 Model 5 Model 6 Model 7

Incom 0.290*** - - 0.024 0.304*** - 0.031
e
Car - 0.354*** - 0.335 - 0.370*** 0.346***
Ed - - - - 0.147 - -
0.118*** 0.155*** 0.156***
R^2 0.84 0.125 0.014 0.126 0.105 0.149 0.149

Regression model with standardized coefficients:

 - Model 1: Jobsat = 2.708 + 0.005*Income
- Model 2: Jobsat = 2.391 + 0.22*Car
- Model 3: Jobsat = 3.405 – 0.134*Ed
- Model 4:
- Model 5: Jobsat = 3.124 + 0.05*Income – 0.168*Ed
- Model 6: Jobsat = 2.821 – 0.177*Ed + 0.023*Car
- Model 7: Jobsat = 0.031*Income + 0.346*Car - 0.156*Ed
Regression model with unstandardized coefficients:
- Model 1: Jobsat = 2.708 + 0.005*Income
- Model 2: Jobsat = 2.391 + 0.022*Car
- Model 3: Jobsat = 3.405 - 0.134*Ed
- Model 4: Jobsat = 2.398 + 0.000*Income + 0.021*Car
- Model 5: Jobsat = 3.124 + 0.005*Income – 0.168*Ed
- Model 6: Jobsat = 2.821 + 0.023*Car – 0.177*Ed
- Model 7: Jobsat = 2.831 + 0.001*Income + 0.022*Car - 0.178*Ed