1 Executive Summary


Embedded within this report is a detailed analysis of Newtown Property prices from June 2017. Here we compare the average price of sold properties, whether carspace affects price value, the cheapest properties sold, which agency earnt the most in the given time period and whether property type affects price.

2 Full Report

2.1 Initial Data Analysis (IDA)

The Newtown property prices dataset comes from data scraped by domain in June 2017. Domain is an Australian digital property portal, trusted with credible house price results and Australian property market news. The data received in the set analyses the property, type, agent, bedrooms, bathrooms, carspots, value and date sold. The dataset includes property prices from one month in June. Not indicating the entire year’s worth of properties sold, limiting the datasets credibility as an indicator of overall property prices in Newtown.

# Given file.xlsx
library(readxl) 
property = read_excel("NewtownJune2017.xlsx")
str(property)
## tibble [56 × 8] (S3: tbl_df/tbl/data.frame)
##  $ Property : chr [1:56] "19 Watkin Street Newtown" "30 Pearl Street Newtown" "26 John Street Newtowmn" "23/617-623 King Street Newtown" ...
##  $ Type     : chr [1:56] "House" "House" "House" "Apartment" ...
##  $ Agent    : chr [1:56] "RayWhite" "RayWhite" "Belle" "RayWhite" ...
##  $ Bedrooms : num [1:56] 4 2 2 1 1 5 1 1 1 3 ...
##  $ Bathrooms: num [1:56] 1 1 1 1 1 1 1 1 1 2 ...
##  $ Carspots : num [1:56] 1 0 0 1 1 1 0 1 1 0 ...
##  $ Sold     : num [1:56] 1975 1250 1280 780 650 ...
##  $ Date     : POSIXct[1:56], format: "2017-06-23" "2017-06-23" ...

Here is a summarised version of the domain dataset from Newtown property prices sold in June 2017.

median(property$Sold)
## [1] 1387.5

The median (middle) price of property prices in Newtown were $1387.5 (thousand).

sd(property$Sold)
## [1] 599.0897

The standard deviation, or how much properties differed from the mean, was $599.0897 (thousand).

IQR(property$Sold)
## [1] 921.75

The IQR (interquartile range) or midspread (middle 50% of data) was $921.75 (thousand).


2.2 Given Research Questions

2.2.1 What was the average price of a property?

# all properties
mean(property$Sold)
## [1] 1407.143
hist(property$Sold)

The average price (mean) of a property in Newtown cost approxiametly $1407.143 (thousand).

2.2.2 Does the amount of carspots affect the price?

The average price of a property with 0 carspots is $1333.421 (thousand).

mean(property$Sold[property$Carspots=="0"])
## [1] 1333.421

The average price of a property with 1 carspot is $1331.379 (thousand).

mean(property$Sold[property$Carspots=="1"])
## [1] 1331.379

The average price of a property with 2 carspots is $1856.875 (thousand).

mean(property$Sold[property$Carspots=="2"])
## [1] 1856.875
boxplot(property$Sold~property$Carspots)

Here is a boxplot of the dataset comparing average property prices in regard to carspots. The average of properties with 1 carspot was actually lower than if a property had 0 carspots. If the property had 2 carspots, the average price was much higher. Therefore, carspots had some affect on house price.

2.2.3 What were the cheapest properties?

Here is the sold prices from cheapest to most expensive.

# Sort all prices
sold = property$Sold
sort(sold)
##  [1]  370  625  645  650  675  692  720  740  740  755  770  780  812  860  861
## [16]  920  935  955  955  999 1100 1240 1250 1280 1309 1315 1370 1375 1400 1460
## [31] 1553 1575 1590 1600 1600 1600 1605 1662 1701 1710 1750 1780 1790 1806 1850
## [46] 1940 1950 1975 2000 2100 2200 2235 2300 2410 2810 3150

Here are the cheapest properties from the dataset; the cheapest sold was 514/88 King Street Newtown.

attach(property)   # The database is attached to the R search path, so variables in the database can be accessed by simply giving their names.
head(property[order(Sold), ][c(1, 6, 7)], 10)
## # A tibble: 10 x 3
##    Property                        Carspots  Sold
##    <chr>                              <dbl> <dbl>
##  1 514/88 King Street Newtown             0   370
##  2 14/163 Australia Street Newtown        1   625
##  3 1/60 Wilson Street Newtown             1   645
##  4 12/2-6 Brown Street Newtown            1   650
##  5 63/3-13 Ersenville Road Newtown        0   675
##  6 113/63-71 Enmore Road Newtown          1   692
##  7 13/20 Fitzgerald Street Newtown        0   720
##  8 4/502 King Street Newtown              1   740
##  9 412/1 Georgina Street Newtown          1   740
## 10 B303/38 Alice Street Newtown           0   755

2.2.4 Assuming commission fees are around 2%, which agency earnt the most over that period?

# Example of extracting Agent sales

sort(property$Agent)
##  [1] "Belle"                  "BresicWhitney"          "EeRealEstate"          
##  [4] "EeRealEstate"           "GerberProperties"       "GreenSquareResidential"
##  [7] "HarrisPartners"         "Iskandar"               "LJHooker"              
## [10] "LJHooker"               "LJHooker"               "LJHooker"              
## [13] "Martin"                 "McGrath"                "McGrath"               
## [16] "McGrath"                "OneAgency"              "PlanetProperties"      
## [19] "R&W"                    "R&W"                    "R&W"                   
## [22] "R&W"                    "Raine&Horne"            "Raine&Horne"           
## [25] "Raine&Horne"            "Raine&Horne"            "Raine&Horne"           
## [28] "Raine&Horne"            "Raine&Horne"            "Raine&Horne"           
## [31] "Raine&Horne"            "Raine&Horne"            "Raine&Horne"           
## [34] "Raine&Horne"            "RayWhite"               "RayWhite"              
## [37] "RayWhite"               "RayWhite"               "RayWhite"              
## [40] "RayWhite"               "RayWhite"               "RayWhite"              
## [43] "RayWhite"               "RayWhite"               "RayWhite"              
## [46] "TraversGray"            "Urbane"                 "Urbane"                
## [49] "Urbane"                 "Urbane"                 "Urbane"                
## [52] "Urbane"                 "Urbane"                 "Viewey"                
## [55] "Viewey"                 "Viewey"

Here are the agent sales for all properties sold in Newtown, sorted by alphabetical order. The most properties were sold by agents Raine&Horne & RayWhite, thus indicating the most commission earnt.

The commission earnt by Ray White during this period was $347.62 (thousand).

sum(property$Sold[property$Agent=="RayWhite"])*0.02
## [1] 347.62

The commission earnt by Raine & Horne during this period was $338.6 (thousand).

sum(property$Sold[property$Agent=="Raine&Horne"])*0.02
## [1] 338.6

Therefore in June 2017, Ray White earnt the most commission in Newtown, earning $347.62 commission from property prices.

2.3 Own Research Question

2.3.1 Does the Type of property affect price?

There are a number of types of property named within this dataset including apartment, unit, house, townhouse and studio.

sort(property$Type)
##  [1] "Apartment" "Apartment" "Apartment" "Apartment" "Apartment" "Apartment"
##  [7] "Apartment" "Apartment" "Apartment" "Apartment" "Apartment" "Apartment"
## [13] "Apartment" "Apartment" "Apartment" "Apartment" "Apartment" "Apartment"
## [19] "House"     "House"     "House"     "House"     "House"     "House"    
## [25] "House"     "House"     "House"     "House"     "House"     "House"    
## [31] "House"     "House"     "House"     "House"     "House"     "House"    
## [37] "House"     "House"     "House"     "House"     "House"     "House"    
## [43] "House"     "House"     "House"     "House"     "House"     "House"    
## [49] "House"     "House"     "House"     "House"     "Studio"    "Townhouse"
## [55] "Unit"      "Unit"
boxplot(property$Sold~property$Type)

A boxplot indicating price and average based on property types in Newtown.

The mean of each property type are indicated below:

mean(property$Sold[property$Type=="House"])
## [1] 1781.059
mean(property$Sold[property$Type=="Townhouse"])
## [1] 1309
mean(property$Sold[property$Type=="Apartment"])
## [1] 835
mean(property$Sold[property$Type=="Unit"])
## [1] 767.5
mean(property$Sold[property$Type=="Studio"])
## [1] 370

The highest price average of properties sold were homes, with an average of $1781.059 (thousand). The singular price of a Townhouse contributed $1309, making it the 2nd highest price average. Apartments had an average of $835 (thousand), Units had an average of $767.5 (thousand), and the studio had a selling price of $370 (thousand).

In conclusion, property type does affect value as Houses had a higher price average than other property types.