MATH2901: Higher Theory of Statistics

- Quiz, worth 5%
- Midterm quiz, worth 20%
- Written assignment, worth 15%
- Final exam, worth 60%

Formally, only one of MATH1231, MATH1241, MATH1251 or DPST1014 is required.

However, I would probably recommend you to have done MATH2011 or MATH2111 as well, not just because some of the content from it appears, but also because you’ll benefit from the mathematical maturity.

Whether you do this course or not, learning some proper statistics beyond what is taught in high school or 1st year maths is always really good knowledge to have. This course is inherently a more applications-focused one, but the first half of this course (probability theory) should appeal to you if you’re more into pure maths as I am. For a variety of reasons, this was the most difficult of the level 2 core maths courses so far for me. (

2x 2 hour lectures, 1x 1 hour tutorial

4/5

Yes, on Blackboard Collaborate.

Dr. Donna Mary Salopek

Nothing too impressive here: some mediocre lecture slides that had typos in them here and there, some tutorial problems with solutions and some notes on how to use R (which were actually very good).

There’s a very comprehensive set of course notes floating around from a previous lecturer of the same quality as the R notes, although you had to find these on your own as they weren’t provided.

0.5/5 - harsh, but unfortunately deserved in my eyes

Not required, but Introduction to Mathematical Statistics by Robert Hogg may be helpful.

21T2

84 DN, which is the most poetic end to this course I could've imagined

5% Mobius Quiz
15% Assignment
20% Midterm
60% Final Exam

MATH1231 or MATH1241 or MATH1251 or DPST1014 (or, in program 3653, MATH1131 or MATH1141

Wanted to do this first while I'm still a little bit mad, don't want to waste energy later getting mad again.

If a course's saving grace and only salvageable positive is the course content, you're doing something wrong. It's a prized asset that should ideally make courses great. Unfortunately, that was the case for this particular course. I want to stick to slagging off the course but it's really tough to do without putting my toe across the line, so I'm going to stick to two main issues:

Problem 1: Assessments
A potential final with a portion on Mobius? That angers me and a lot of the students (from the little I have heard). (also the reason why the 2/5 rating remains tentative). This also comes after the uproar surrounding the midterm on Mobius. While some of my problems with the midterm include some self-sabotage marks wise, it's tough to objectively ignore the associated issues with a) demonstration of knowledge and b) results distribution.

Problem 1a) Mobius is such a reductive platform that is good only for quizzes that were basically free marks anyway. For actual demonstration of what you've learned, it's genuine garbage. For maths, you need to show thought processes and working out, which was only available on one question in the midterm. Hearing that it will likely compose a part of the final pisses me off a lot. Again, the platform is reductive as hell and marks a huge departure from in person exams. The best way to mimic these and allow to you use the skills taught in each course is to have moodle submissions of pictures of your work (which literally every other course uses; I've done this in every maths course after math1a/1b (admittedly only two) and it is so much better).
Problem 1b) This is somehow worse than problem 1a). We were told we weren't allowed to review our midterm because a) questions were going to be reused in later course offerings and b) it wouldn't have helped us learn anyway. If there's anything I've learned in general from school, it's that everyone learns differently. Not even

2 x 2hr + 1 x 1hr lectures
1 x 1hr tutorial

3/5

Yes

Dr Donna Mary Salopek

Lecture slides, R manual, course formula sheet, tutorial questions are provided and sufficient

0.5/5 (down from pre-exam 2 because of the exam)

The only creditable aspect of the course was that the final had a better format than expected ie. file submissions. That is the only part which I will give any credit for (the relevant pre-exam criticism can be rescinded). It should still be noted that Mobius file submissions have limitations on filenames and is in general clunkier than a Moodle submission (personal preference only). However, the organisation of the final was still disastrous. Key edits to the paper (for example a probability distribution function that wasn't actually a probability distribution function) came frustratingly late and forced me (and I presume at least a few other students, if not more) to lose time both fixing my answers to reflect the edits and on other questions since I had to fix my answers. It's telling that I wasn't surprised by this, nor the fact that there were no immediate concrete concessions made to alleviate potential losses. I quote: 'No one will be penalized if you did not see the corrections', which sounds to me like errors that reflected the original paper on the questions that had typos were not penalised, but other questions would be; hence, the second point I make (about losing time on other questions by altering answers to reflect corrections) was not accounted for by any publicly announced concession. While the exam was more than doable, the organisation of it was essentially a microcosm of the course as whole.

Above materials

21T2

80 DN

- 1 quiz (worth 5%).
- 1 midsem (worth 20%).
- 1 assignment (worth 15%).
- 1 final exam (worth 60%).

MATH1231 or MATH1241 or MATH1251 or DPST1014.

This is one of the core level 2 courses for any student undertaking a maths degree and it introduces students to the theory behind some statistical concepts. The course is split into two components: the first half covers the basics of probability theory, while the second half dives into the heart of statistical analysis. By the end of the course, you'll feel more confident with all things statistics.

I actually enjoyed the course for what it is, an introductory statistics course. I found some results really interesting and non-trivial, and it's made me appreciate the stats a lot more than when I began the term. I found the first half of the course a lot more interesting but that's probably because I found the first half more intuitive than the second half. The lecturer is chill af (legit a dude swore on the first day of lectures and the lecturer replied with "yeah same" lmao).
The assessments weren't too difficult either, it was really just testing to see if you actually paid attention in lectures. So in all, I really enjoyed the course. Would recommend.

6 hours (2 x 2 hour lectures, 1 x 1 hour lecture, 1 x 1 hour tutorial).

3/5

Yes.

Dr. Libo Li.

Lecture notes were sufficient.

4/5.

No required textbook.

20T2

80 DN

Prerequisites:

I personally don't like statistics, so I'm quite biased, but the second half of the course (applied statistics) was quite boring and dry. There were some parts that interested me, but they weren't examinable (more exotic forms of convergence), and we didn't go into much detail. Some of the marking schemes used for the final and midterm were sort of unfair, and the marking for the assignments was really harsh to make up for the simple questions asked. I wouldn't recommend the course unless you have a natural interest in statistics, but MATH2901 is certainly more interesting than MATH2801 if you like pure mathematics. The course is pretty integration-heavy for the first half, and a lot of the second half is calculus and computation-heavy. Not a course I'd do a second time personally, but a useful course nonetheless.

2x 2hr Lecture, 1x 1hr Tutorial

2.5/5

Yes - screen and voice recorded, plus document camera when used.

Dr. Libo Li

Lecture notes and course notes (pretty similar) posted online, and some (read: few) past final exams available. A few past midterms supplied, and solutions to the problems in the course notes.

2.5/5

Note: I don't use textbooks and can't comment on their usefulness. None prescribed, but useful references:

2018 S1

92 HD

20% In-lecture Mid-semester exam, 2 x 10% Assignments (2017 - Group assignments. 2016 and prior - Individual.)

One of MATH1231/MATH1241/MATH1251. As the course outline is combined with MATH2801, no explicit requirement of a mark of 70 was stated. You should be familiar with basic probability and are expected to know elementary calculus techniques such as integration by parts.

This is one of the three compulsory Level 2 courses to all mathematics disciplines, offered in semester 1. It is the higher counterpart of MATH2501. Students intending to major in mathematics and statistics must take this course or the standard version.
This course can (and

2 x 1 hour + 1 x 2 hour (Total 4 hours) lectures, 1 hour tutorial

2/5

Yes (First time this has happened as the lecturer was encouraged by students to use the document camera)

Dr. Libo Li

An online course pack is uploaded onto Moodle and to be honest it has too much. The lecturer is nice and is selective of content to teach, and his notes that he uploads should be used as the primary reference. Whilst rarely, sometimes the course pack also explains differently to how the lecturer teaches it (in particular hypothesis testing).

5/5

N/A

2017/1

95 HD