To prepare for this Discussion, assume that your company is relocating you to a

Question

To prepare for this Discussion, assume that your company is relocating you to a new city and state with an increase in salary. Assume a 15% salary increase for you, and that your spouse, if working now, can receive an equivalent salary with no difficulty after moving to the new location. Because you have been guaranteed that your stay will be at least three years, you begin thinking about buying a home there. One major problem is that you have no knowledge about the geographical area. Purchasing a home is a significant investment decision. Therefore, before you decide on your purchase, you need to have knowledge about the area.

Choose any city you wish to serve as your fictitious relocation site and research the current statistical information you will need to make an informed decision. Research the municipal, public safety, real estate, and other websites for information on the location of your choice. Also, consider visiting the Sperling’s Best Places website for additional information. Note the statistical facts you feel will help you to make an educated decision.

Explanation / Answer

We can use multiple linear regression model to predict the house price depending on the relevant independent variables such as:

We used the Boston housing data to build the predictive model and estimate the price of any given home to have a fair idea about the price.

R -code for model building:

#use Boston housing data from: "http://www.amstat.org/publications/jse/v19n3/decock/AmesHousing.xls"
data <- read.csv("C:/Users/xxx/Desktop/data.csv")
View(data)

#filtering the data (removing House ID & S.N.)
data1=data[,3:19]
attach(data1)

#assessing correlation:
plot(SalePrice, Total.Bsmt.SF)
plot(SalePrice, Lot.Area)
plot(SalePrice, Garage.Area)
plot(SalePrice, Overall.Quality)

#built regression model:

summary(lm(SalePrice~.,data = data1))
#remove insignificant variables
data2=data1[,1:10]
summary(lm(SalePrice~.,data = data2))

The final model output:

Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -1.055e+05 6.707e+03 -15.733 < 2e-16 ***
Lot.Area 7.277e-01 9.675e-02 7.521 7.17e-14 ***
Total.Bsmt.SF 3.468e+01 2.062e+00 16.820 < 2e-16 ***
Kitchen.AbvGr -2.553e+04 3.685e+03 -6.928 5.24e-12 ***
TotRms.AbvGrd 9.081e+03 5.510e+02 16.481 < 2e-16 ***
Fireplaces 1.113e+04 1.251e+03 8.895 < 2e-16 ***
Garage.Cars 8.808e+03 2.144e+03 4.108 4.10e-05 ***
Garage.Area 4.156e+01 7.437e+00 5.588 2.50e-08 ***
Overall.Quality 2.616e+04 7.336e+02 35.665 < 2e-16 ***
Overall.Condition 1.666e+03 6.541e+02 2.547 0.0109 *
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 38170 on 2918 degrees of freedom
(2 observations deleted due to missingness)
Multiple R-squared: 0.7725,   Adjusted R-squared: 0.7717
F-statistic: 1101 on 9 and 2918 DF, p-value: < 2.2e-16

R-sq is 77% & F-stat is also significant thus model is good to use.

Lot Area Total Bsmt SF Kitchen AbvGr TotRms AbvGrd Fireplaces Garage Cars Garage Area Overall Quality Overall Condition Year Built Bldg Type House Style Roof Style Bsmt Exposure Heating Central Air

Related Questions

Navigate

• Browse (All)
• Browse T
• Subjects

---

---

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.