Codd’s Corner, Venn’s Den, and Bayes Boudoir

Codd’s Corner, Venn’s Den, and Bayes Boudoir

Yeah right.  Names to our new meeting rooms in the new offices ‘ere at Adroit Towers.  Famous geezers from world of database and analysis.  To our 3 heroes of data, logic, non-conformity and eccentricity we will salute on our meeting room doors.

Let’s ‘ave some respect, please.

Don’t know Coddwho they are? – then bloody well read on and get urself ejucated….

Let start with Mr Edgar “Ted” Codd, who died in 2003, inventor of the relational database. Where would we be without some Codd eh? Forget the silicon chips. This plucky chap took on IBM, who refused to take on his relational model ‘cos they wanted to continue with loot from their IMS/DB.  Codd was so ballsy he showed the customers anyway, and IBM catapulted/capsized/capitulated (ok “gave in”).  They then even tried to ostichize ‘im by isolating ‘im from his developers. But Codd didn’t care, he created SEQUEL, (yeah we don’t know who created PREQUEL), but the SQL was better than the PRQL.  Quite quickly a Mister Larry Ellison of Relational software Inc, launched his Oracle Database, and reached the market before SQL/DS– because by then-the proprietary status of the original name, SEQUEL had been renamed SQL(BTW.  We think Mr Ellison is a great guy, for hiring that great British sailor Sir Ben Ainslie and helping Oracle USA to victory in 2013 against the Kiwis – especially as they beat us at rugby. And we’re not going to ask about where the cod were, we’ve done one fish pun already).

However we do note (from Wikipedia) that Mr Codd continued to develop and extend his relational model, sometimes in collaboration with Christopher J. Date.  Dates with cod – odd recipe?  Anyway one of the normalised forms, the Boyce–Codd normal form, is named after him – so Date was Boyce? (we’re confused).

Needless to say though, whenever we do database designs and play around with our crows feet, code up some T_SQL or normalise our forms we are in ‘omage to the old boy.  So we reckon that Mr Codd is well worthy of the database halls of fame, and should do an OLAP of honour  – dash, did I forget to mention he invented the term “Online analytical processing” (OLAP) and wrote the “twelve laws of online analytical processing?. Well he did, the superstar. Respect.

Onto our next, Hull’s finest, Mr John Venn 1834-1923

Lots of peepsVenn can be a bit down on Hull.  Not us.  Mr John Venn came from there, along with Hull Kingston Rovers.  Mr Venn was the sporty inventor of cricket bowling machines and set theory (apparently he liked tennis too).  Whilst in Cambridge, we took a punt that Mr Venn did not spend his life going round in overlapping circles.  He worked out that the overlap bit could be used to display shared properties (way before shared mortgages).  So for example, suppose you use three overlapping circles (A,B, and C ) to represent different types of birds, such as native garden birds, migratory birds and birds of prey, respectively. You could start to see how the overlapping categories create different sets, and which sets would be appealing to cats, or perhaps those who would just like to play with booles. Mr George Boole, to be exact, who had all sorts of hooks and quantifiers appealing to the feline nature, hence why he was known as being a smooth operator. But enuff of Sade or ‘im.   We note from the venerable Wikipedia that:

“In 1866, Venn wrote Logic of Chance, a work that was considered highly original and influential on the development of the theory of statistics. He also wrote Symbolic Logic, in 1881, and Principles of Empirical Logic in 1889..  In 1883, he was elected a member of the Royal Society for his work in maths and logic.” Seems logical.  He later became an actor, and appeared in the first episode of Star Trek.  (Only kidding, but we can imagine him there, in the Starship enterprise, crashing into another starship, a huge interstellar intersect, where all the crew had to Klingon).

Today we use Venn diagrams quite regularly to show clients their different customer overlaps – as long as they don’t ‘ave more than seven, otherwise our software implodes. Quite right, a superb player, and one we regularly visualise even today on the intersection of every motorway roundabout, especially that Magic Roundabout in Swindon wot he inspired.  “’ats off to you, Mr Venn”. Respect.

Pay attention. Our final hero (for today) of the analytical world, is Mr Thomas Bayes 1701–1761, probably the best statistician in the world never to have seen a beer advert, but eponymous creator of all things Bayesian, with a little help from Mr Pierre Simon Laplace.

In the begBayesinning, Mr Bayes, from Tunbridge Wells was not particularly angry. In fact Thomas wrote the catchy 18th Century bestseller “Divine Benevolence, or an Attempt to Prove That the Principal End of the Divine Providence and Government is the Happiness of His Creatures (1731)”.  Ok I’m fibbing, it wasn’t busting the shelves at Waterstones.  But Thomas did go on in a non-conformist free-thinking approach to problems wot we admire.

I refer again from the fount of all wisdom, Mr Jimmy Wales, proud creation..

Bayesian probability is the name given to several related interpretations of probability, which have in common the notion of probability as something like a partial belief, rather than a frequency. This allows the application of probability to all sorts of propositions rather than just ones that come with a reference class. “Bayesian” has been used in this sense since about 1950. Since its rebirth in the 1950s, advancements in computing technology have allowed scientists from many disciplines to pair traditional Bayesian statistics with random walk techniques. The use of the Bayes theorem has been extended in science and in other fields. Bayes himself might not have embraced the broad interpretation now called Bayesian. Mathematician Pierre-Simon Laplace pioneered and popularised what is now called Bayesian probability. It is difficult to assess Bayes’s philosophical views on probability, since his essay does not go into questions of interpretation. There Bayes defines probability as follows (Definition 5).

The probability of any event is the ratio between the value at which an expectation depending on the happening of the event ought to be computed, and the value of the thing expected upon its happening.

In modern utility theory, expected utility can (with qualifications, because buying risk for small amounts or buying security for big amounts also happen) be taken as the probability of an event times the payoff received in case of that event. Rearranging that to solve for the probability, Bayes’s definition results.

Today we undertake “econometric modelling” using Bayes techniques, or even look for missing Air France aircraft…and quite frankly we don’t really like to talk about the posterior predictive distribution in polite company. Or observe it (it’s a new data point)…

Posterior Predictive Distribution



See what we mean?  Let’s hear thepraise for Mr Bayes, our odds on favourite, welcome to our boudoir…respect.