Who wants to win £194,375?

In an earlier post I included a link to Oscar predictions by film critic Mark Kermode over the years, which included 100% success rate across all of the main categories in a couple of years. I also recounted his story of how he failed to make a fortune in 1992 by not knowing about accumulator bets.

Well, it’s almost Oscar season, and fabien.mauroy@smartodds.co.uk pointed me to this article, which includes Mark’s personal shortlist for the coming awards. Now, these aren’t the same as predictions: in some year’s, Mark has listed his own personal favourites as well as what he believes to be the likely winners, and there’s often very little in common. On the other hand, these lists have been produced prior to the nominations, so you’re likely to get better prices on bets now, rather than later. You’ll have to be quick though, as the nominations are announced in a couple of hours.

Anyway, maybe you’d like to sift through Mark’s recommendations, look for hints as to who he thinks the winner is likely to be, and make a bet accordingly. But if you do make a bet based on these lists, here are a few things to take into account:

  1. Please remember the difference between an accumulator bet and single bets;
  2. Please gamble responsibly;
  3. Please don’t blame me if you lose.

If Mark subsequently publishes actual predictions for the Oscars, I’ll include a link to those as well.


Update: the nominations have now been announced and are listed here. Comparing the nominations with Mark Kermode’s own list, the number of nominations which appear in Mark’s personal list for each category are as follows:

Best Picture: 1

Best Director: 2

Best Actor: 1

Best Actress: 2

Best supporting Actor: 3

Best supporting Actress: 1

Best Score: 2

In each case except Best Picture, there are 5 nominations and Mark’s list also comprised 5 contenders. For Best Picture, there are 8 nominations, though Mark only provided 5 suggestions.

So, not much overlap. But again, these weren’t intended to be Mark’s predictions. They were his own choices. I’ll aim to update with Mark’s actual predictions if he publishes them.

And the winners are…

soy

In previous posts I discussed the Royal Statistical Society’s ‘Statistic of the Year’ award. I’m now grateful to Richard.Greene@smartodds.co.uk for having pointed out that the winners for 2018 have now been announced. They are as follows:

International award: 90.5%

UK award: 27.8%

Before reading any further you might like to have a quick guess at where those statistics derive from and why they might have been selected.

Actually, the two statistics have contrasting motivations: one is pretty depressing, while the other is a cause for some optimism. Maybe this balance was intentional. The 90.5% is the proportion of plastic waste that has been produced and not recycled. The 27.8% is the peak percentage of all electricity produced in the UK due to solar power on 30 June this year, which actually made it the largest single form of energy production in the UK on that particular day.

You can find a fuller explanation of the awards here. This also includes a list of ‘highly commended’ nominations. I guess my favourite is 16.7%, which is the proportional reduction in the number of Jaffa Cakes in a McVities’ Christmas tube due to shrinkflation. This is the process whereby manufacturers hide actual price increases by reducing the volume of a product – often by stealth – while keeping the price the same. Who knows why so many manufacturers should suddenly be adopting this strategy?

Meanwhile, remember to take note of any potential nominations for the 2019 awards.

Christmas quiz

I mentioned in a previous post the Royal Statistical Society (RSS), which is the UK’s foremost organised body of statisticians. In addition to its role in promoting and publishing all-things statistical, it is also famous for one other thing: its annual Christmas quiz, which is widely considered to be one of the toughest quizzes around. It’s been going for 25 years and is famous enough that it gets reported in full in the Guardian.

Though produced by the RSS, the questions have nothing to do with statistics, and not much mathematics either. That said, the questions do require a good general knowledge, logical thinking and a capacity to approach problems laterally; skills that are useful for statisticians. My personal total score for the quiz over the last 5 years or so is zero. 

So, the 2018, 25th anniversary, edition of the quiz is now available here. If you like a good challenge you might enjoy having a go at it. Good luck, and remember that you can’t possibly do worse than me. I’ll post a link to the solutions once they are available.


Just to give you some idea of the types of questions you’re likely to face in the quiz, here’s a question from the 2017 edition:

POLYMERISATION
If 5 is IHNTOBBTTAS, and 10 is IDAATINELR, what will 20 be?

Can you get the answer? There’s a clue in the question title. Once you’ve had enough, scroll down for the solution.

|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|

 

 

 

SOLUTION:

The polymer £5 note introduced in 2016 by the Bank of England features the quote “I have nothing to offer but blood, toil, tears and sweat” (initial letters IHNTOBBTTAS), while the new polymer £10 note features the quote “I declare after all there is no enjoyment like reading!” (initial letters IDAATINELR). The polymer £20, due for release in 2020, will feature the quote “Light is therefore colour” – so the answer is “LITC”.

Obviously I failed to find this solution in much the same way as I failed to find any solution to any of the questions in each of the quizzes for the last five years. I didn’t look at the quizzes in previous years, but you might extrapolate my more recent scores to get a reasonable estimate of what my score would have been if I had.

If you want further practice, you can find the complete 2017 version of the quiz here and the solutions here.

 

 

Fake news

A while back, when I was touting the idea of Smartodds loves Statistics to the Smartodds management, I also asked for ideas for possible posts. Nity.Raj@smartodds.co.uk very kindly suggested a post based on the following analysis, which had actually been doing the rounds on social media circles for some time.

madcow

The map on the left shows the UK by county according to whether the county voted predominantly ‘leave’ (blue) or ‘remain’ (yellow) in the 2016 referendum. The map on the right shows incidences of mad cow disease in the 1992 outbreak: counties that were affected are coloured black; those unaffected are coloured grey. It’s brilliant. As you can see, there’s a near-perfect correspondence between counties affected by mad cow disease in 1992 and counties that leant towards Brexit in the referendum 24 years later.

Brilliant, but sadly not true.

Actually, it’s literally ‘too good to be true’. There’s not just a near-perfect correspondence between the two figures, there’s a perfect correspondence. If I take the figure on the right and colour the black bits blue and the grey bits yellow I get an exact replicate of the figure on the left. Even if there really were a strong relationship between mad cow disease and Brexit, the nature of random variation means it’s virtually impossible we’d get a perfect tie-up like this. Someone has simply taken the correct map on the left, changed blue for black, yellow for grey, and changed the legend.

So, what probably was intended just as a bit of a joke gained momentum via social media, and ends up being ‘Fake News’. Unfortunately, this ends up being a bit counterproductive, both for Statistics as a science, and in the argument against Brexit. Because if it’s easy (and correct) to dismiss this analysis as fake news, it becomes much easier to dismiss all scientific analyses, most of which are serious and accurate, in the same way.

Remember this?

Does this have anything to do with Smartodds? Well, yes and yes. Yes, because Statistics is the core activity of Smartodds provision to its clients, and since Statistics is a joined-up-subject, anything with a statistical element to it is of relevance. And yes in a more direct way, because looking for patterns in data that are too good to be true is an important service to clients. Not so much in historical results data, but in live market data, where prices that seem too good to be true, probably are due to match-fixing. So what seems like a fantastic price is actually a terrible price because the match is fixed against that particular outcome. Identifying implausible patterns in market data is not such a black-and-white (and blue-and-yellow) process as for the maps above, but the principle is much the same, and we’ll perhaps look at it in greater detail in a future post.


By the way: October 20th