Exam

The main exam sitting for Inf1-DA completed this morning. The ITO will now gather the 300 or so exam scripts and pass them to the marking team to start work. We expect to take a week or two on the first round of marking; followed by internal and external review of the results, with particular attention to borderline cases. These are then combined with marks from your other courses to determine progression to second-year study. Once this is all completed then Informatics results will be released through EUCLID/MyEd.

By our current schedule we expect to return Informatics 1 results some time between 27 June and 3 July: and in any case as soon as possible within that.

Link: More information on exam results

If your exam sitting today was seriously affected by ill-health or other circumstances outside your control then please mail immediately the Informatics Student Support Team at inf-sst@inf.ed.ac.uk or contact your Personal Tutor.

Link: More information on special circumstances

To everyone taking the course: thank you for taking part — in lectures, tutorials, on Piazza, by email, and dropping by to ask questions. You are what makes Inf1-DA happen, you’ve done a great job at that, and I look forward to seeing you later on in you degree study here.

References
Screenshot of openclipart search results for "bird feeder" Punxsutawney Phil
High-precision information retrieval at Openclipart Punxsutawney Phil inspects his shadow. Picture by Anthony Quintano on Flickr

Tutorial Notes and Additional Exam Preparation Tutorial

I’ve posted notes for this week’s tutorial, on Statistical Analysis, to the tutorial web page.

A number of tutors have offered to run an additional exam preparation tutorial, using a mock paper from an earlier year. To participate you would work through that paper over the next couple of weeks; send your written script to a tutor; they mark it; and you get it back for discussion and feedback in a tutorial during revision week at the end of April.

Tutors are still setting this up: I’ll announce details when that’s done and you will be able to sign up if you are interested.

Link: Tutorial Exercises

Student Course Feedback

Screenshot of survey page
All Course Surveys

Please spend time giving written feedback on Inf1-DA in the online survey. This is organised centrally by the University, with all results sent to the individual course organiser and to the Director of Teaching. Submissions are anonymous. I read every comment individually, and for Informatics courses we post your advice online to help other students choosing courses for the future.

(more…)

Tutorial Notes: Solutions to Practice Exam Questions

I’ve posted some notes on solutions to the practice exam questions from this week’s tutorial exercises. These are based on the sheets you had at the tutorials, but without the detailed mark counts and with improvements following feedback from students and tutors. In particular I’ve tried to be more precise and informative about:

  • The choice of tables to use when modelling the ER diagram for Q1(c);
  • Different ways to write the XPath query for Q2(c)(i) on lines spoken by Rosencrantz.

The final set of tutorial exercises, for Week 11, will be online later today.

Link: Tutorial Exercises

Lecture 19: The χ2 Test; Correlation and Causation

Title slide
Slides : Recording

This lecture followed on from Friday’s in looking at the use of hypothesis testing to detect correlations in data. The first section examined the χ² test for working with qualitative data, using two demonstration examples: possible correlation between coursework submission and exam grades; and the discovery of collocations in large text corpora.

The second part of the lecture looked in more detail at some of the risks in misapplying statistical tests. Hypothesis testing can be a tremendously sensitive and powerful tool for discovering new science and identifying the connections between events. However, when used poorly it becomes misleading and unhelpful. The lecture covered a range of concerns about these risks: confusing correlation with causation; what p-values can tell us and what they can’t; when statistical “significance” is really about being statistically detectable; p-hacking, data dredging, outcome switching; and the current replication crisis in some experimental sciences. There is also hope and success, though: in the discovery of robust results through meta-analysis; the active discussions around reproducibility and predictive power in scientific research; and the many projects to record trials, replicate results, and improve publication of both negative and positive outcomes.
(more…)

Lecture 18: Correlations and Hypothesis Testing

Title slide
Slides

Today’s lecture presented the idea of correlation in data sets: observing correlations through scatter plots; measuring them with the correlation coefficient; and using hypothesis testing to see whether that gives evidence to distinguish them from chance coincidence. In this way we get increasingly more precise and sensitive measures for detecting correlation.

Although, remember: correlation does not imply causation. More on that next time.
(more…)