9.

Using the Excel file Weddings, apply the Excel Regression tool using
the wedding cost as the dependent variable and attendance , income,
age, value rating as the independent variable.

a. Interpret all key regression results, hypothesis tests, and confidence

intervals in the output.

Multicollinearity test for independent variables

Coefficientsa

Unstandardized Standardized
Coefficients Coefficients Collinearity Statistics
Toleranc
Model B Std. Error Beta t Sig. e VIF
1 (Constant) 910.091 11713.15 0.078 0.939
4
Couple's 0.325 0.080 0.646 4.049 0.001 0.497 2.012
Income
Bride's age -399.720 441.619 -0.120 -0.905 0.376 0.721 1.387
Attendance 46.719 28.835 0.263 1.620 0.121 0.479 2.086
Value 837.652 1055.154 0.103 0.794 0.437 0.755 1.325
Rating
a. Dependent Variable: Wedding cost
 VIF for all the variables is less than 5 -> Multicollinearity didn’t occur,
remove 0 variable

Model Summaryb
Change Statistics
R Durbin
Square F Sig. F -
Adjusted R Std. Error of Chang Chang Chang Watso
Model R R Square Square the Estimate e e df1 df2 e n
1 .864a 0.747 0.696 $7,297.5601 0.747 14.748 4 20 0.000 1.845
0
a. Predictors: (Constant), Value Rating, Attendance, Bride's age, Couple's Income
b. Dependent Variable: Wedding cost
74% of the variation in the wedding cost can be explained by the
independent variable

Hypothesis tests

H0: β1=β2=β3=β4=0

H1: At least 1 βi≠0

ANOVAa
Model Sum of Squares df Mean Square F Sig.
1 Regression 3141674730.78 4 785418682.695 14.748 .000b
1
Residual 1065087669.21 20 53254383.461
9
Total 4206762400.00 24
0
a. Dependent Variable: Wedding cost
b. Predictors: (Constant), Value Rating, Attendance, Bride's age, Couple's Income

Sig.<0.05 => reject H0, support H1 => mô hình hồi quy là phù hợp

H0: βi=0 (there’s isn’t a significant relation between dependent and

independent variables)

H1: βi≠0 (there’s isn’t a significant relation between dependent and

independent variables)

Coefficientsa
Standardized 95.0% Confidence
Unstandardized Coefficients Coefficients Interval for B
Lower Upper
Model B Std. Error Beta t Sig. Bound Bound
1 (Constant) 910.091 11713.154 0.078 0.939 - 25343.302
23523.121
Attendance 46.719 28.835 0.263 1.620 0.121 -13.429 106.867
Couple's Income 0.325 0.080 0.646 4.049 0.001 0.158 0.493

Bride's age -399.720 441.619 -0.120 -0.905 0.376 -1320.921 521.482

Value Rating 837.652 1055.154 0.103 0.794 0.437 -1363.362 3038.665

In all the sig. statistic, with the confidence interval of 95%, there’s only 1
variable with the sig. smaller than 0.05 (reject H0 for the variable couple’s
income and support with others variable). in other words, the model has 1
statistically significant cause variables for the outcome variable "Wedding
cost".

multiple linear regression model: Wedding cost= 910.09 + 46.72 x

attendance + 0.325 x Couple’s income – 399.72 x Bride’s age + 837.65 x
value rating + £.

b. Analyze the residuals to determine if the assumptions underlying the

regression analysis are valid.
Linearity: - scatterplot have a linear trend and there is no pattern in residual
plot

Normality of error: – residual histogram appears slightly skewed but is not a

serious departure

Homoscedasticity: residual plot shows no serious difference in the spread of

the data for different X values.
Independence of error: because the data is cross sectional, we can assume
that this assumption holds.

c. Use the standard residuals to determine if any possible outliers exist.

There’re two outliners because the standard deviation is larger than 2.

d. If a couple is planning a wedding for 175 guests, age 28, rating 3, income
60.000$, how much should they budget?

With the multiple linear regression model:

Wedding cost= 910.09 + 46.72 x attendance + 0.325 x Couple’s income –

399.72 x Bride’s age + 837.65 x value rating + £.

The wedding cost for the given statistic= 910.09 +46.72 x 175+ 60000 x
0.325 -399.72 x 28 + 837.65 x 3= 19906.88

In conclusion, the adjected budget for 175 guests, age 28, rating 3, income
60.000$ is about 19906.88 dollars.