College

As a data scientist, you collect 60,000 data points for an online real estate listing company on 5,000 newly listed single-family homes (SFH) within the Central Valley. You develop the following inverse demand models to help find undervalued homes:

[tex]\[
\begin{array}{l}
\text{Model 1:} \\
y = 300 - 0.1x_1 + 200x_2 + 100x_3 + 0.05x_4 \\
\\
\text{Model 2:} \\
y = 300 - 0.1x_1 + 200x_2 + 100x_3 + 0.05x_4 + 0.04x_5 + 75x_6 - 0.1x_7 + 150x_8 - 20x_9 - 30x_{10} - 50x_{11}
\end{array}
\][/tex]

Data Table: Inverse Demand [tex]\((P^D)\)[/tex] Variables for Single-Family Homes

[tex]\[
\begin{array}{c|l|c|c|l|l}
\text{Data} & \text{Model Variables} & \text{Coefficient} & \uparrow \text{ or } \downarrow & \text{Endo- or Exogenous} & \text{Shift or Movement} \\
\hline
y & \text{Monthly Mortgage Price} & - & - & \text{Endogenous} & \text{Movement} \\
x_1 & \text{Qty. of SFH in the Market} & 0.1 & & & \\
x_2 & \text{No. of Bedrooms} & & & & \\
x_3 & \text{No. of Bathrooms} & & & & \\
x_4 & \text{Lot Size in Ft}^2 & & & & \\
x_5 & \text{Home Size in Ft}^2 & & & & \\
x_6 & \text{No. of Parking Spots} & & & & \text{Shift} \\
x_7 & \text{Miles Away From Freeway} & 0.1 & \downarrow & \text{Exogenous} & \\
x_8 & \text{Home Has a Pool} & & & & \\
x_9 & \text{Years Since Home Built} & & & & \\
x_{10} & \text{Mortgage Interest Rates} & & & & \\
x_{11} & \text{Neighborhood Crime Rate} & & & & \\
\end{array}
\][/tex]

Answer :

Sure! Let's walk through the process of understanding and analyzing the inverse demand models provided for single family homes within the Central Valley. The goal is to identify how each variable in the models affects the monthly mortgage price, represented as "y" in the equations.

### Models Overview:
We have two inverse demand models to consider:

Model 1:
[tex]\[ y = 300 - 0.1x_1 + 200x_2 + 100x_3 + 0.05x_4 \][/tex]

Model 2:
[tex]\[ y = 300 - 0.1x_1 + 200x_2 + 100x_3 + 0.05x_4 + 0.04x_5 + 75x_6 - 0.1x_7 + 150x_8 - 20x_9 - 30x_{10} - 50x_{11} \][/tex]

### Variables and Coefficients:
- [tex]\( x_1 \)[/tex]: Quantity of SFH in the Market, coefficient -0.1
- [tex]\( x_2 \)[/tex]: Number of Bedrooms, coefficient 200
- [tex]\( x_3 \)[/tex]: Number of Bathrooms, coefficient 100
- [tex]\( x_4 \)[/tex]: Lot Size in Ft², coefficient 0.05
- [tex]\( x_5 \)[/tex]: Home Size in Ft², coefficient 0.04 (in Model 2)
- [tex]\( x_6 \)[/tex]: Number of Parking Spots, coefficient 75 (in Model 2)
- [tex]\( x_7 \)[/tex]: Miles Away From Freeway, coefficient -0.1 (in Model 2)
- [tex]\( x_8 \)[/tex]: Home Has a Pool, coefficient 150 (in Model 2)
- [tex]\( x_9 \)[/tex]: Years Since Home Built, coefficient -20 (in Model 2)
- [tex]\( x_{10} \)[/tex]: Mortgage Interest Rates, coefficient -30 (in Model 2)
- [tex]\( x_{11} \)[/tex]: Neighborhood Crime Rate, coefficient -50 (in Model 2)

### Analyzing the Effects:
- A negative coefficient indicates that as the variable increases, the monthly mortgage price decreases. Conversely, a positive coefficient means an increase in the variable leads to an increase in the monthly mortgage price.

Model 1 Analysis:
- [tex]\( x_1 \)[/tex]: An increase will decrease "y" because of the -0.1 coefficient.
- [tex]\( x_2 \)[/tex]: An increase will increase "y" due to the +200 coefficient.
- [tex]\( x_3 \)[/tex]: An increase will increase "y" because of the +100 coefficient.
- [tex]\( x_4 \)[/tex]: An increase will increase "y" owing to the +0.05 coefficient.

Model 2 Analysis:
- [tex]\( x_5 \)[/tex]: An increase will increase "y" due to the +0.04 coefficient.
- [tex]\( x_6 \)[/tex]: An increase will result in an increase in "y" at a larger change due to a +75 coefficient.
- [tex]\( x_7 \)[/tex]: An increase will decrease "y" because of the -0.1 coefficient, indicating it's less desirable if farther from the freeway.
- [tex]\( x_8 \)[/tex]: An increase will strongly increase "y" due to the +150 coefficient, reflecting added value from a pool.
- [tex]\( x_9 \)[/tex]: An increase, meaning the house is older, will decrease "y" as indicated by the -20 coefficient.
- [tex]\( x_{10} \)[/tex]: An increase in mortgage interest rates will decrease "y" because of the -30 coefficient, which could reflect reduced affordability.
- [tex]\( x_{11} \)[/tex]: An increase in crime rates will decrease "y" due to the -50 coefficient, indicating lower desirability in areas with higher crime.

This breakdown helps in understanding which factors influence the expected mortgage price positively or negatively and by how much, providing a foundation for identifying undervalued homes.