Exam 1

1.1 Introduction

This document shows how COVID-19 has had an impact on the Cincinnati Housing Market. Economic policies during this pandemic have may have influenced the prices of residential properties surrounding Xavier’s campus. Data provided by the Hamilton County Auditor for this analysis.This analysis will allow the reader to better understand the neighborhoods affected, including how different home sizes and featutes are affected by price changes.

1.2 Packages

Packages
readr
stringr
ggplot2
dplyr
lubridate

2.1 Data

http://asayanalytics.com/xu_prop-csv

2.2 A.

Data Errors: Reason:
Unit ID: Cannot be a date
Date: Cannot occur in the future

2.2 B.

New Variables:

Single Date

Multi Family Dummy Variable

Discrete Variables

3.1 Square footage

homes %>%
  ggplot(aes(x = finished_sqft))+
  geom_histogram()+
  stat_bin(bins = 30)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

Sqft is not normally distributed with a clear right skew

3.2

homes %>%
  ggplot(aes(x = neighborhood, y = full_bath / bedrooms)) +
  geom_bar(stat = "summary", fun = "mean")+
  ylab("Ratio")
## Warning: Removed 2 rows containing non-finite values (`stat_summary()`).

I suspect that neighborhoods such as Mt. Adams and Walnut Hills have more homes that are occupied by younger occupants or “roommates” rather than families, meaning that there are fewer bedrooms and more bathrooms per house.

3.3

homes %>%
  ggplot(aes(x = month(month,label = TRUE),y = value))+
  geom_bar(stat = "summary", fun = "sum")+
  facet_wrap(~ neighborhood)+
  xlab("Month")
## Warning: Removed 1986 rows containing non-finite values (`stat_summary()`).

In the different neighborhoods, it is apparent that there is a higher sum of home sales in the summer months compared to other seasons. This is especially apparent in Norwood and Hyde Park

4.1

If you were gifted a residential property in this area and you intended to sell it for the highest price:

a: In what neighborhood would you want it to be located?

homes %>%
  ggplot(aes(x = neighborhood, y = value))+
  geom_bar(stat = "summary", fun = "mean")
## Warning: Removed 1986 rows containing non-finite values (`stat_summary()`).

Mt. Adams

b: What features (size, rooms, bedrooms, etc.) would you want it to have?

homes %>%
  ggplot(aes(x = bedrooms, y = value))+
  geom_bar(stat = "summary", fun = "mean")
## Warning: Removed 1986 rows containing non-finite values (`stat_summary()`).

homes %>%
  ggplot(aes(x = full_bath, y = value))+
  geom_bar(stat = "summary", fun = "mean")
## Warning: Removed 1986 rows containing non-finite values (`stat_summary()`).

7 full bath

c: How old would you want it to be?

homes %>%
  ggplot(aes(x = yr_blt, y = value))+
  geom_point()+
  geom_smooth()
## `geom_smooth()` using method = 'gam' and formula = 'y ~ s(x, bs = "cs")'
## Warning: Removed 1986 rows containing non-finite values (`stat_smooth()`).
## Warning: Removed 1986 rows containing missing values (`geom_point()`).

1920s

d: What time of year or day of the week would you want to sell (or does it matter?)

homes %>%
  ggplot(aes(x = month, y = value))+
  geom_bar(stat = "summary", fun = "mean")
## Warning: Removed 1986 rows containing non-finite values (`stat_summary()`).

Summer time

5.1

How many homes have been purchased by an LLC each year?

homes %>%
  ggplot(aes(x = year,y = str_count(purchaser,"LLC")))+
  geom_bar(stat = "summary", fun = "sum")

This number has been increasing since 2018

How has the average home value changed since 2018?

homes %>%
  ggplot(aes(x = year, y = value))+
  geom_bar(stat = "summary", fun = "mean")
## Warning: Removed 1986 rows containing non-finite values (`stat_summary()`).

Home value has been increasing since 2018