Reflection of PSDA- project 2

Hello, I am Simon, this is a reflection of Probability & Statistical Data Analysis subject, project 2. It is about inferential statistic. I will used 4 tests in this project which are hypothesis testing 2 sample, correlation, regression, and chi-square test from a raw datasets about Malaysian undergraduate study contains the variable:

1. Gender
2. Age
3. Previous qualification certificate
4. Current academic field of study
5. Is the current course being your choice during application before?
6. Satisfaction level with current course
7. CGPA in previous institute
8. Current CGPA
9. Frequency of co-curriculum participant in previous institute
10. Frequency of co-curriculum participation in current institute
11. Average study duration in last institute everyday (in minutes)
12. Average study duration in current university everyday (in minutes)
13. Style of learning

From the variables above, I will choose certain of them to complete the test, and I used R programming to help me in this finding. At the end of finding, I had a very interesting result which is the relationship between the CGPA which is the student’s performance, I expected the CGPA is highly dependent on the study duration, but the result of the test surprised me. CGPA does not be affected by their study duration. So, my own conclusion is there must be other reason or issue is affecting the student’s CGPA such as parents’ education level, friends, maybe the involvement of curriculum and any other reason.  

During the analysis process, I learn how to do it in R programming and understand well how to use the test in real life data instead of the data given in the slide. Besides that, time management is quite important, we were giving a long duration to finish this project, it is about 1 months more. But due to some uncontrollable issue, assignment, and project of other subjects, we must start planning earlier and finish it as soon as possible but must ensure the quality of the project. Next, these tests will be helpful in data analysis to figure out a useful result in improving something or solve the problem. For example, from my test in the project, I knew that the CGPA is not highly dependent on the study duration, therefore I might think of other reason to improve my CGPA in this case. Furthermore, in my regression test, I had the conclusion that the study duration is highly dependent on their satisfaction level to their current studying course. Means if the satisfaction level is higher, they are willing to spend more time on study. This is quite interesting because usually student will choose the course that they might think is easier or will be paid with higher salary after graduation instead of thinking of whether they interested in it. Conclusion, this a good and nice experience from this project in analyzing process, I learn how to improve my analyzing skill and have a useful conclusion from the testing result.

SIMON CHONG KAI YUEN

A19EC3028

6/28/2020