You are on page 1of 9

PBL assignment

Vance Kang
Research Qn
• For couples looking for resale
because BTO/SBF is hard to get
• Is there a significant difference in
prices in HDB resale flats between
sectors 'Balestier, Toa Payoh,
Serangoon’ and 'Geylang, Eunos’.
• From the boxplot it seems to have
a difference but shall be using
independent T test to be sure
Preparing the dataset

• In order to make a more


representative study shall be reducing
noise of the dataset by limiting certain
conditions of the HDB
transactions(the conditions are
bellow)
• The "MRT dist category2"]=='Near’
means only HDB flats with an MRT
within 500m are considered
• Other conditions such as tranc year
after 2021, age of flat and floor area
are also chosen.
• They are then split into 2 datasets:
A. 'Balestier, Toa Payoh,
Serangoon’
B. 'Geylang, Eunos'
Information/distribution of dataset
To check for validity of use of
independent T-test
• Conditions for Using independent t-test
1. Need to ensure that the two samples are normally
distributed
1. As seen bellow, both samples are normally distributed
The p-value of the Levene’s test is less than 0.05,
suggesting that there is a significant difference
between the variances of the two groups. Therefore,
we’ll use the Welch t-test, which is for variances that
To check for is different

equal
variance
The test statistic turns out to be 5.19
and the corresponding p-value is
4.975e-07. Here the p-value is less than
0.05 hence we could reject the null
hypothesis of the test and the
conclusion that there is a significant
Conclusion difference between the resale price of
area of sectors 'Balestier, Toa Payoh,
Serangoon’ and 'Geylang, Eunos’

There is a possibility of Type I error


Statistics
Script
Reference
• Welch's t-Test in Python – GeeksforGeeks
• Normal Probability Plot - GeeksforGeeks

You might also like