Introduction

The data set that I am using takes individale home sales from Ames Iowa. The data set contains the sale price about 2,930 homes that were sold in the area as well as other factors that can be used to understatnd the price. This can range from the neighborhood the home is in to the year it was built, to the size of the home, to the number of rooms. This is can be useful to see what gan give homes value or what some charicterists are common amoung low value homes or neighborhoods. I would like to find out what factors raise home prices the most, and persinaly if I would value them at the same level. I would like to know what some key chariteristct that make up low value homes are. What are some charictersistic that made an non-normal sale type?

EDA

library(tidyverse)
## ── Attaching packages ────────────────────────────────────────────── tidyverse 1.3.0 ──
## ✓ ggplot2 3.3.2     ✓ purrr   0.3.4
## ✓ tibble  3.0.3     ✓ dplyr   1.0.2
## ✓ tidyr   1.1.2     ✓ stringr 1.4.0
## ✓ readr   1.3.1     ✓ forcats 0.5.0
## ── Conflicts ───────────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()
library(leaps)
AmesHousing<-read.csv("/Users/timogunsalus/Downloads/AmesHousing.csv", header = TRUE)
#data(AmesHousing)
#attach(AmesHousing)

First I wanted to look at some low, medium, and high neighborhoods spisificly

ggplot(data = AmesHousing, mapping = aes(SalePrice, Neighborhood, color=MS.Zoning))+
  geom_point()

I chose to use theis neighorhoods: Old Town, which is cheaper and has promintly residential medium density housing. Sawyer which is cheap and has prodomiantly residential low density. Northwest Ames which is medeamly priced and has prodomiantly residential low density housing. Finaly, Northridge Heights which is expencsive and has prodomiantly residential low density housing.

#selecting only those 4 neighborhoors
target <- c("OldTown", "Sawyer", "NWAmes", "NridgHt")
Cheap.Exp <- filter(AmesHousing, Neighborhood%in%target)

Next I wanted to look at the types of houses in the different neighborhoods.

ggplot(data = Cheap.Exp, mapping = aes(SalePrice, Bldg.Type, color=Neighborhood))+
  geom_jitter()

Northridge Heights has single family homes and townhouses but no duplexes or single family homes that were converted into multifamily homes. Also the Townhouses on the end seam like they could be more expensive.

Finaly I wanted to know how much a neiborhood contrubes to the selling price so looking at the overall quality of the home might help show this.

ggplot(data = Cheap.Exp, mapping = aes(SalePrice, Overall.Qual, color=Neighborhood))+
  geom_jitter()

The quality of homes seams to have a fairly linear relationship with the price until the max quality is hit. I dont know how qulity was mesured but it does show that the neighborhood with other expenceve homes tends to drive price up even if the quality is not as nice. This could be do to factors like better schools or proximity to parks.