Tim Harford in the FT wondered whether in our enthusiasm for Big Data, we have forgotten some statistical principles:
Four years after the original Nature paper was published, Nature News had sad tidings to convey: the latest flu outbreak had claimed an unexpected victim: Google Flu Trends. After reliably providing a swift and accurate account of flu outbreaks for several winters, the theory-free, data-rich model had lost its nose for where flu was going. Google’s model pointed to a severe outbreak but when the slow-and-steady data from the CDC arrived, they showed that Google’s estimates of the spread of flu-like illnesses were overstated by almost a factor of two.
The problem was that Google did not know – could not begin to know – what linked the search terms with the spread of flu. Google’s engineers weren’t trying to figure out what caused what. They were merely finding statistical patterns in the data. They cared about correlation rather than causation…
..But a theory-free analysis of mere correlations is inevitably fragile. If you have no idea what is behind a correlation, you have no idea what might cause that correlation to break down.
Reverse Polish Notation was first suggested by three American mathematicians Arthur Burks, Don Warren and Jesse Wright in 1954, but was not fully elucidated until 1957 when Charles Hamblin, an Australian philosopher and computer scientist, implemented it as an algorithm in a computer language called GEORGE. With his training in formal logic, Hamblin was clearly aware of Lukasiewicz’s work, as were several others who came independently to similar conclusions. As its name implies, RPN is a “postfix” form of notation, with the operators placed after the operands. Thus, x+y becomes xy+.
Skeletons of Black Death victims, mostly from the original, most deadly 1348 outbreak, which were found by the Museum of London in an excavation for London Crossrail revealed a surprising amount of information about life and death at the time:
Many of the bodies showed signs of poor health and of having jobs that involved heavy manual labour, the Queen’s University researchers said, noting a high rate of back damage and strain.
Four out of the 10 remains analysed are from people that grew up outside the capital, as far north as Scotland, showing that, just as today, London drew people from across the country.
Something to remind Australia’s life insurance actuaries that there is such a thing as an insurance cycle – global reinsurance rates for Property and Casualty reinsurance continue to fall with no end in sight.
The rates reinsurers charge customers are under pressure as low interest rates drive capital market investors, such as pension funds searching for above-average returns, into their market. Below-average catastrophe claims have also left the industry, which shoulders risks for primary insurers in return for a share of the premiums, with abundant funds.
And finally, a new aspiration – having your own lego minifig! Possibly even better than a Nobel Prize… probably better if you are a parent to small children, anyway. The Atlantic writes about Sylvia Earle:
The first thing you should know about Sylvia Earle is that she has a LEGO figurine modeled after her. One that has little yellow flippers instead of little yellow feet.
But you should also, if you don’t already, know many more things about Sylvia Earle. You should know that she has been a pioneer of deep-sea exploration—becoming, essentially, the maritime equivalent of an astronaut.
For good sources of great articles, try: