Tutorial and Coursework Solutions

Notes and solutions are now up for Tutorial 8: Statistical Analysis.

I have also written a Feedback Report on the written assignment, which contains a detailed guide to solutions and also some comments on the range of student answers. Please attend your listed tutorial session this week, and your course tutor will return your work to you individually.

Links:Tutorial exercises; Coursework assignment

Front page of tutorial notes
Tutorial 8: Statistical Analysis
Notes and Solutions
Front page of feedback report
Coursework Assignment
Solutions and Feedback

Request for Feedback

Three separate requests for your comment and contribution, all looking for as many responses as possible.

  • Inf1-DA final lecture — which topics to review? Poll closes 5pm Thursday.

  • Informatics course surveys. A single page form, confidential anonymous feedback directly to the lecturer. Fill out one for each course you have done this semester.

    Results of “What would you say to students considering this course?” are posted online for next year’s students.

  • EUSA Teaching Awards: nominate personal tutors, course tutors, individual courses, lecturers, and more in eight different categories. Over two thousand nominations so far: add yours.

    Oh, and Maths are currently winning on “most nominations per student”. Just saying.

Links: Final lecture topics; Course surveys; Award nominations

Lecture 18: Hypothesis Testing and Correlation

Title slideWhere the last lecture was about summary statistics for a single set of data, we now address multi-dimensional data with several linked sets of values among which we might look for correlations. This leads into several more sophisticated questions which are key to the effective application of statistics: how do we identify potential effects like correlation; how do we know when we have found evidence for an effect; and what might this tell us about any causal connections?
Continue reading Lecture 18: Hypothesis Testing and Correlation

Tutorial Solutions

I have now posted a set of notes and solutions to this week’s tutorial exercises, on Information Retrieval.

The Inf1-DA assignment is due for submission on Thursday. Please remember to write on the front your name, matriculation number, course tutor name, group number, and the course code INF1-DA. Hand in your work by 4pm Thursday to the box outside the ITO.

Some answers to questions students have asked about writing up the assignment.

  • Handwritten and typed submissions are both fine. In the exam you will have to write answers by hand. If this will cause you particular difficulty, please get in touch (and also see this web page for things we can do to help).
  • You can use pen or pencil as you wish. I recommend pen for text, and pencil for diagrams. If you use pencil for everything there is a small risk that your work may become partially erased and illegible.
  • There is no alternative of electronic submission for this coursework.
  • You can submit as early as you like. ITO staff check the box regularly, and stamp all work when it arrives.

Links:Tutorial exercises; Coursework assignment

Tutorial Exercises

The next set of exercises are up on the tutorial web page. These require you to carry out some statistical analysis of survey data about last year’s Inf1-DA students. Some of this statistics was covered in today’s lecture slides; the rest is in the slides for Friday and Tuesday. I’ve put these slides up in advance on the lecture web page so that you can look ahead. In addition, the Examples and Solutions sections of the tutorial exercises contain complete worked examples of all the necessary statistical tests.

The Inf1-DA assignment continues to run this week. Please remember to write on the front your name, matriculation number, course tutor name, group number, and the course code INF1-DA. Hand in your work by 4pm Thursday to the box outside the ITO.

If you have any questions or problems with this, then please do go along to InfBASE, ask on Piazza, or ask your course tutor.

Links:Tutorial exercises; Coursework assignment

Contribute to the Spoken British National Corpus

Logo for British National Corpus 2014Fancy being recorded for posterity as an example of real-life speakers of British English? Then sign up for the new Spoken British National Corpus. Researchers at Lancaster and Cambridge are compiling a new, publicly accessible corpus of English speech.

“We aim to encourage people from all over the UK to record their interactions and send them to us as MP3 files. For each hour of good quality recordings we receive, along with all associated consent forms and information sheets completed correctly, we will pay £18.”

If you’re interested, read their web page and email corpus@cambridge.org for more information.

Link: Announcement of Spoken BNC

Inf1-DA 2014–2015