Introduction Advanced Data Analysis:

Charalampos (Charis) Chanialidis

Outline of slides

Who am I (and how to pronounce my name)?
Objectives of the course
Structure of the course
Timetable
Assessment
Outline of lab session topics

What’s in a name?

My full name is Charalampos Chanialidis.

Unfortunately, Greek names are longer than average.

Most Greek names though, can be shortened by using the front end or the back end of the full first name.

In my case, the name Charalampos is shortened into Charis (pronounced as Harrys).

Feel free to call me Chari (Harry).

First useless information of the day: Wikipedia has an article referring to the saint I was named after. There are 7 different versions of how my name is spelled. Charalampos is not one of them.

Second useless information of the day: The meaning of my name is “to shine from happiness” from the Greek words for happiness (chara) and to shine (lampo).

My office is located at the 2nd level (Room 324), my twitter handle is @cchanialidis, and my email is charalampos.chanialidis@glasgow.ac.uk

Structure of the course (Slide I)

A week before each lab, I will upload the material we will work on where I will present the following week’s subject.

On Monday’s “lecture” we will discuss the material I have already uploaded and ask you some questions about it.

We will also use something called Plickers, but more on that later.

Structure of the course (Slide II)

Our “lectures” will be every Monday, between 15:00 and 16:00, on the ground floor of the School of Mathematics and Statistics building (room \(110\)).

Our lab sessions will be every Thursday, between 11:00 and 13:00, on the ground floor of the School of Mathematics and Statistics building (computing lab \(117\)).

These labs allow for group work and we will take advantage of that.

Structure of the course (Slide III)

There will be group projects for the course. It’s goal is for you to increase your independence and responsibility for own learning, communicate, cooperate and work with each other.

One of these group projects will be assessed.

You should think of the day as a mixture of the technical and showstopper challenges on The Great British Bake Off.

You should be able to produce a finished product with limited instructions and show off your skills.

There will be no eliminated groups.

Assessment

There will not be a final examination at the end of the course.

There will be biweekly quizzes on Moodle, counting for \(15\%\) of the final mark altogether.

There will be \(1\) in-class group project that will be assessed, counting for \(15\%\) of the final mark altogether.

There will be \(1\) in-class individual project, counting for \(30\%\) of the final mark.

There will also be an out-of-class individual final project, counting for \(40\%\) of the final mark.

The final project will be different for Level \(4\) and Level M students.

Outline of session topics

Date	Topic
September 27 (Week \(7\))	Data visualisation techniques
October 4 (Week \(8\))	non-assessed group project on Generalised linear models
October 11 (Week \(9\))	non-assessed group project on Generalised linear models
October 18 (Week \(10\))	in-class group project (15%)
October 25 (Week \(11\))	non-assessed group project on Clustering
November 1 (Week \(12\))	non-assessed group project on Clustering
November 8 (Week \(13\))	in-class individual project (30%)
November 15 (Week \(14\))	Bayesian Statistics (part I)
November 22 (Week \(15\))	Bayesian Statistics (part II)
November 29 (Week \(16\))	Building Shiny applications with R
November 29 (Week \(16\))	start of out-of-class individual project (40%)
December 21 (Week \(19\))	end of out-of-class individual project

There will also be 4-5 Moodle quizzes throughout the semester (worth \(15\%\) in total).

Objectives of the course

Provide the opportunity for critical thinking and independent learning.

Develop expertise in formulating and implementing statistical approaches to practical problems in a wide variety of subject areas.

Develop written and oral skills of presentation and communication.

Prepare you for a future role in business or academia as a practising statistician.

In other words, I want you to hate me but at the same time appreciate the course and understand its benefits.

Things not to say during the semester

“Can I come by your office so you could explain to me what is a generalised linear model?”

“I have found these comments, related to clustering, on a website. I am thinking of putting them in my report; are the comments correct?”

“I was planning to submit the final project early but I realised that I have to learn some things by myself in order to submit it, and I couldn’t find the answers online. Can you tell me the answers, so I can submit the project early since I have two other projects over Christmas?”

Tips for the course (and the semester in general)

Be curious. Take initiatives even if the end result isn’t as good as expected.

Don’t be afraid to fail. “Success is the ability to go from failure to failure without losing your enthusiasm.”

Try to spend some time approaching the same issue by looking at it from different angles. “If you can’t explain it simply, you don’t understand it well enough.”

Things to do before our lab sessions

The first lab session is on the \(27\)th of September at 11am.

During that meeting, you will just be assigned to a group and we will also have a look at data visualisation.

On the second lab session, you will work as a group on a non-assessed project about generalised linear models (4th October 2018).

You would have to read the uploaded material on Rpubs, and work on the Further reading section at the Theory page.

What questions do you have for me?