Semester 2

PROBABILITY & STATISTICAL DATA ANALYSIS Project 2

                        USA House Sales Price

                   & How other factors affect its variation

This is a page that used to demonstrate my work in PSDA project 2. You can find slides, reflections, videos by scrolling down

 

 

Name: Lee Sze Yuan

Metric Number: A19Ec0068

Section: 02

LECTURER: Dr Chan Weng Howe

Welcome To MY PSDA Project 2

Project 2: USA House Sales Price & How other factors affect its variation

Reflection

 

Skill

Throughout this whole project, I learned how to how to use R to perform advanced data analysis. This is also my first time doing data analysis on big dataset that has at least 10000 data entries. Then, I really want to say that through this project, I learned the importance of hypothesis testing and learned how to apply it on our daily life situation

Favourite Things

Besides, the things I love the most is linear regression because it can help us to predict value! It can explain how a variable changed and how it affected by other variables. Then after some self-research and study, I also realised actually linear regression can be considered as a simple machine learning model too. I get really excited on this and wish to learn more about regression

 

Knowledge

Then, in this project, I also learned a lot of things about house sales price. For example, I learned that not only total square feet, number of floors are affecting the house sales price. I also learned that house grade, house conditions can affect it too. Then, I also learned that there is actually many unforeseen factors like market, economic conditions are affecting house sales price of a country.

 

Challenges

About challenges faced in this project, in my opinion, I think that the biggest challenge is that find out that the tests I proposed in my proposal cannot be carried out properly in R programming. Then, I have to read a lot of articles and surf internet to find out suitable solutions. Besides, there is also some challenges that I realised the null hypothesis or alternative hypothesis actually is not suitable for my stud. Then, or when I find out that the actual results is different from the expected result.

 

Thoughts

Lastly, I want to say that through this project, I also learned and understand more the condition of property market in Malaysia. Although, the population I study is USA and there are difference too, but the knowledge I learned can also applied in Malaysia too

Details

Result Presentation

Report Showcase

R Scripts

Datasets