Answer Sheet Group Number: - 6 - Names of Team Members: - Hongru Bi, Yangxi Gan, Tara Kelley, Jie Xu Data Set - Arlhomes1

Answer Sheet
Group Number: _6____
Names of Team Members: _ Hongru Bi, Yangxi Gan, Tara Kelley, Jie Xu
Data Set__ArlHomes1________________
Attach all the R/Stata Regression output to the answer sheet.

1. For the sample data use R/Stata to find the mean price, square footage, number of
bedrooms, and number of bathrooms. (Attach the R/Stata output to the answer sheet.)

Price Square Feet Beds Baths
Average 623,887 1865 3.25 2.153

2. Use R/Stata to estimate the following four models. Round the coefficients to the nearest
whole number. (Attach the R/Stata output to the answer sheet.)

(a) Model 1:
Priceˆ=𝛽0+𝛽1Sqft

𝑷𝒓𝒊𝒄𝒆ˆ
=45522.27+310.16Sqft

(b) Model 2:
Priceˆ=𝛽0+𝛽1Sqft+𝛽2Baths

=50973.29+212.69Sqft+81897.32Baths

(c) Model 3:
Priceˆ=𝛽0+𝛽1Beds+𝛽2Baths

=13115+ 73712Beds+172432Baths

(d) Model 4:
Priceˆ=𝛽0+𝛽1Sqft+𝛽2Beds+𝛽3Baths

𝑷𝒓𝒊𝒄𝒆=ˆ
29068.6+193.9Sqft+15395.5Beds+85066.1Bath
s

3. For Model 4 in (d) above, interpret the coefficients for SqFt, Bed, and Bath.

Sqft: One additional square foot of area is associated with 193.9 dollars more of price.
Bed: One additional bed is associated with 15395.5 dollars more of price.
Bath: One additional bath is associated with 85066.1 dollars more of price.

4. (a) Fill in the table below with the Standard Error of the estimate and Adjusted
R2
given by R/Stata for each model. (Attach the R/Stata output to the answer sheet.)
Standard Error Adjusted
R2

Model 1 87,160 0.8427
Model 2 78,980 0.8709
Model 3 95,250 0.8122
Model 4 79,730 0.8684

Model 1:

Model 2:

Model 3:

Model 4:

(b) Based on you answer in (a) determine the best model for predicting Price. Explain
briefly.
Based on the information determined within part a, for each of the four models, it
appears that model 2 would be the best model for predicting the price. This is because model
2 has the lowest standard error and the highest adjusted R-squared numbers. These two
factors are important because a lower standard error indicates that there is a more accurate
representation of the data and a higher adjusted R-squared value indicates that there is a
higher amount of variability that is being explained within the model.

5. Use each model to estimate the price of a 2000 square foot house with 3 bedrooms and 2
bathrooms.

(a) Model 1
(Price)^=45522.27+310.16Sqft
=45522.27+310.16*2000
=$665,842.3

(b) Model 2
(Price)^=50973.29+212.69Sqft+81897.32Baths
=50973.29+212.69*2000+81897.32*2
=$640,147.93

(c) Model 3
(Price)^= 13115+ 73712Beds+172432Baths
= 13115+73712*3+172432*2
=$579,115

(d) Model 4
(Price)^= 29068.6+193.9(Sqft)+15395.5(Beds)+85066.1(Baths)
=29,068.6+193.9*2000+15,395.5*3+85,066.1*2
=$633,187.3

6. For the multiple regression model determine which variables are individually significant in
predicting Price at the 5% significance level. Explain you answers briefly.

(a) Model 3

Both the “Beds” and “Baths” variables are individually significant. The “Beds”
variable has a p-value “0.0037” which is lower than the significance level of 0.05. The
“Baths” variable has a p-value “4.14 *10-9” which is also lower than the significance level of
0.05.

(b) Model 4

The p-value for the Beds is higher than 5% which means that it is not individually
significant in this mode. The p-values for the Square footage and Baths are both below 5%,
which makes them both individually significant in this model.

7. For each multiple regression model, conduct a test of joint significance at the 5%
significance level to determine if the variables are jointly significant predictors of
Price. Explain your answers briefly.

a. Model 2
 H0: β1= β2=0, H1: at least one β is not equal to 0
 ANOVA

 Considering that the p-value for this regression model is 8.1424*10 , making
-16
it lower than the significance vale of 0.05, we reject the null hypothesis.

 Because of this, it can be concluded that at the 5% significance level, Sqft and
Baths are jointly significant in explaining the Price.

(b) Model 3
 H0: β1= β2=0, H1: At least one β is not equal to 0
 ANOVA

 Since the significance F (p-value) is “3.94239*10 , which is lower than the
-13
significance value of 0.05, we reject the null hypothesis.

 Therefore, we can conclude that at the 5% significance level, “Beds” and
“Baths” are jointly significant in explaining “Price”.

Answer Sheet Group Number: - 6 - Names of Team Members: - Hongru Bi, Yangxi Gan, Tara Kelley, Jie Xu Data Set - Arlhomes1

Uploaded by

Copyright:

Available Formats

Answer Sheet Group Number: - 6 - Names of Team Members: - Hongru Bi, Yangxi Gan, Tara Kelley, Jie Xu Data Set - Arlhomes1

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Answer Sheet Group Number: - 6 - Names of Team Members: - Hongru Bi, Yangxi Gan, Tara Kelley, Jie Xu Data Set - Arlhomes1

Uploaded by

Copyright:

Available Formats

Answer Sheet

it lower than the significance vale of 0.05, we reject the null hypothesis.

significance value of 0.05, we reject the null hypothesis.

You might also like