Skip to content

How funny are these jokes? Statistics PMCC

November 17, 2012
If you’re reading this, there’s a good chance you’ve seen the survey I tweeted out about rating how funny some jokes are recently.

This post is to do three things:

  1. Share the results from my ‘How funny are these jokes’ survey to use with my year 12 stats students
  2. Remind you how awesome twitter is
  3. Thank the many people that answered/re-tweeted the link

I created a survey involving seven jokes that I like (sorry to those of you who thought the students chose the jokes – that will be the next one) and asked people to rate them on a scale from 0 to 4. I tweeted the link to it at about 7:45 am on Friday morning and by the time it came to their lesson at 12:10pm I had over 100 responses. I also set up a few scheduled tweets to go out through out the morning.

I am genuinely astonished that so many people answered it for me and I’m sure it was partly to do with the fact that it was about jokes but, never-the-less, it’s still impressive and I’m very pleased. As I’m writing this summary, there are over 200 responses and the link has been re-tweeted at least 60 times.

Again, thank you and, if you’re looking for a bunch of data from real people, quickly I can highly recommend twitter!

On to the results (raw data in excel file at end).

A number of responses had missed out rating one or two of the jokes so, in discussion with my class, we decided it’d be easier to just delete those ones. I have no idea who the people rating the jokes were really although it’s probably fair to say that a lot of the internet responses are from people who are maths teachers, connected to maths in some other way or a teacher. This may be significant as you’ll see later. Also, I doubt that very many of the respondents are under 18 due to the nature of my twitter following base.

So, which of the jokes won?
A quick reminder of the jokes:
1) I can’t stand Russian dolls. They’re so full of themselves.
2) My cat’s a genius. I asked her what 2 minus 2 was and she said nothing.
3) Someone complimented me on my driving today. I got back to the car and there was a little sign saying “Parking: Fine”, which was nice of them.
4) I used to train racing snails. One day, I took the shells off to see if they’d go faster. It didn’t really work and, if anything, it made them more sluggish.
5) I’m very good at maths. I understand 110% of it.
6) Cheer leading exams are easy. You go in and shout “Give me an A”.
7) An ex-student of mine said he’d been doing a building course and could build me a ‘wishing wall’ in my garden. I thought, bless him. He means well.

I’ve (mean) averaged the results for each joke and a score of 0 was ‘not funny at all’, 4 means ‘hilarious’.
For the students, I asked them to rate each joke on a scale from 0 to 4 as well and then we totalled their scores (see below). It’s worth mentioning that I told them the jokes rather than them reading them. I think this has a particular impact on the cheer leading joke. 
I then gave the students the internet averages for the first six jokes. We left their scores as totals (for 17 students) as this highlighted the fact that the linear scaling of averaging the score wouldn’t affect the PMCC. They calculated the PMCC and also a regression line to see if their rating of jokes could be used to predict the internet’s rating of the seventh joke. It came out to be a pretty high correlation and the prediction wasn’t that good but was ok (it was 0.2 under).

There was lots of interesting discussion about the nature of the sample and what could be done to improve the estimates. We decided that including the age of the person and whether they were connected to maths may be useful to know. We also wondered (but haven’t looked at yet) whether the prediction may be better depending on which joke we excluded in the first instance. We were also wondering which pair of jokes had the highest correlation (ie if you found the first joke funniest, can we predict which you’d put second?) I’m pretty sure that the Russian doll joke won something at the Edinburgh fringe festival which may well be significant (looking at the results).

I’m tempted to get them to ask the same jokes to people their own age or, perhaps, an old fashioned survey of younger students. I may well get them to choose some jokes that you internet people will find funny, based on the previous sample of jokes.

Essentially, quite a fun lesson which was only really possible (especially at such late notice) due to twitter. Thank you all again for your help.

Excel file with data:


From → Uncategorized

Leave a Comment

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s

%d bloggers like this: