- Average: 39.5

- Minimum: 0

- Maximum: 83

- Number with 44 or less: 813 [56.5%]

- Number with 45 & higher: 627 [43.5%]

- Number with 50 and higher: 472 [33%]

--------------------------------

We assume that most of those with 0 are candidates who did not turn up.

So, for the 1316 candidates who scored more than 0

- Average: 43.5

- Minimum:5

- Maximum: 83

- Number with 5 to 44: 689 [52.4%]

- Number with 45 & higher: 627 [47.6%]

- Number with 50 and higher: 472 [36%]

One should explain me why they can always (i.e. each year) have a kind of Gaussian curve around 40-50 marks

ReplyDeleteBecause with large numbers of candidates, most statistical processes tend to a Gaussian (see the Central Limit Theorem), while the papers are similar as between years, as is the mode of preparation of the students?

ReplyDeleteI find strange how the centre of the Gaussian is always just below 50%.

ReplyDeleteBut even stranger is the dip in 45-49! Either it is a statistical fluke, or grades 45-49 are being reviewed...

If that were the case, you should be able to see whether "missing" 45-49 papers have been added to the Gaussian bins either side. It's usually easy to tell whether someone's been massaging the raw data. Pete - can you subtract your gaussian from the bins, so we can see whether there is a "regrade" effect?

ReplyDeleteActually, I should hope that certain grades, let's say 40 to 50 are checked more carefully than other grades, considering the huge importance.

ReplyDeleteSo I don't find it strange, it confirms what I would find normal