Scribd
Upload
7 views

Tutorial 4

Uploaded by

mashiringwaninyasha2003
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
7 views

Tutorial 4

Uploaded by

mashiringwaninyasha2003
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

HSATS112-tut4 (KRM/E-learning)

DEPARTMENT OF MATHEMATICS AND COMPUTATIONAL SCIENCE

REGRESSION ANALYSIS AND ANOVA (HASTS112)

Tutorial 4

1. Consider the following data set, where Y is the dependent variable and X is the regressor.

Y 4 8 5 9 10
X 2 3 4 6 8
Suppose the data can be described by model yi   0  1 X 1i   i where  i ~ N(0, σ2) and Cov(
i ,  j )  0 if i≠j.

a) Express the above model in matrix form.

b) Using matrix approach, find the least squares estimates of  .

c) Using matrix approach, construct the ANOVA table and test for the significance of the
regression line using α = 0.05.
d) Test whether the intercept of the line is zero. State your null and alternative hypotheses.
2. In a small-scale regression study, the following data were obtained:

X1i 7 4 16 3 21 8
X2i 33 41 7 49 5 31
Yi 42 33 75 28 91 55

Suppose the data can be modeled by a multiple linear regression model.

(a) Express the regression model in matrix form, defining all the terms.
(b) Find the least squares estimates of β, given that,

𝟑𝟒. 𝟓𝟕𝟖𝟓𝟓𝟕𝟒 −𝟏. 𝟔𝟓𝟎𝟖𝟗𝟐𝟔𝟖 −𝟎. 𝟔𝟓𝟕𝟎𝟒𝟎𝟐𝟐


(X1X)-1 =[−𝟏. 𝟔𝟓𝟎𝟖𝟗𝟐𝟕 𝟎. 𝟎𝟖𝟎𝟑𝟎𝟕𝟗𝟔 𝟎. 𝟎𝟑𝟏𝟏𝟐𝟕𝟔𝟑 ]
−𝟎. 𝟔𝟓𝟕𝟎𝟒𝟎𝟐 𝟎. 𝟎𝟑𝟏𝟏𝟐𝟕𝟔𝟑 𝟎. 𝟎𝟏𝟐𝟔𝟖𝟓𝟎𝟏

(c) Construct the ANOVA table and test for the significance of the regression line using
α=0.05.
(d) Test the hypothesis H0:β2=0 versus H1: 𝛽2 ≠ 0 at α=0.05.
(e) Find the 95% confidence interval for the intercept and test whether it is significant.

3. Use data in question 2 above, to fit a multiple linear regression model using SPSS and
compare results with those in question 2.

4. An auctioneer of rugs kept records of his weekly auctions in order to determine the
relationships among price, age of carpet or rug, number of people attending the auction,
and number of times the winning bidder had previously attended his auctions. He felt that,
with this information, he could plan his auctions better, serve his steady customers better
and make a higher overall profit for himself. Using SPSS, a multiple linear regression
HSATS112-tut4 (KRM/E-learning)

relating price to age, audience size, and previous attendence was fitted to the data. The
following is partial SPSS output:

Model Summary

Std. Error of the

Model R R Square Adjusted R Square Estimate

1 .961a .924 .912 147.676

a. Predictors: (Constant), Previous Attendance , Audience size, Age

ANOVAb

Model Sum of Squares df Mean Square F Sig.

1 Regression 5288169.883 3 1762723.294 80.829 .000a

Residual 436163.451 20 21808.173

Total 5724333.333 23

a. Predictors: (Constant), Previous Attendance , Audience size, Age

b. Dependent Variable: Price

Coefficientsa

Standardized

Unstandardized Coefficients Coefficients

Model B Std. Error Beta t Sig.

1 (Constant) 207.729 115.939 1.792 .088

Age 7.484 1.501 .524 4.988 .000

Audience size 10.547 2.395 .446 4.403 .000

Previous Attendance 15.336 9.458 .108 1.621 .121

a. Dependent Variable: Price

a. Write down the equation of the fitted regression line.


b. Test the significance of the regression model, using 𝛼 = 0.05.
c. Are all the regression coefficients significant? If your answer is No, state independent
variables which must be retained in the model and those that have to removed from
the model.
d. State the coefficient of determination and comment.

“The End”

You might also like