As Australia takes control of the search for Malaysian Airlines flight MH-370 in the Indian Ocean and as the theories get ever more conspiratorial comes a suggestion from Nate Silver’s new website FiveThirtyEight that if Australia and the other nations search for the missing jet use Bayesian statistical methods they will be shorten the time to finding the answers to what happened.
FiveThirtyEight says: “Bayesian inference formalizes what will seem, to many unfamiliar with it, like common sense. Its founding principle is that most new situations can be assessed and assigned probabilities: How likely is this restaurant to be good? How likely is this cough to be a cold?”
It’s the kind of conditional probability we all go through each week when we are doing our footy tips.
At the beginning of the season it is difficult because you have less information to go on – think GWS beating the Swans over the weekend. But as the season unfolds and as we are able to overlay more data with what we have already and get better probability on the chance of an outcome so we can build a stronger map of what the expected outcome will be. For example GWS might be having a good season by the middle of the year when next they face the swans increasing the probability that Round 1 was not a fluke.
But as FiveThirtyEight says, predicting the outcome such as that of a footy match or the probability of a good meal in a restaurant requires:
calculation of a single probability. Targeting a search in an area requires a probability estimate for every point in that area, really a probability distribution. Initially, we might guess that the probability is uniform: The object of interest is equally likely to be at any point. Then we update that distribution based on new information, such as — in the case of a missing plane — flight path, wind, ocean flow and which areas have been searched already.
This approach has helped find sunken treasure, men overboard and crucially in this instance missing planes like the Air France Flight 447 which crashed back in 2009 on a flight from Rio to Paris with 228 people on board.
Lawrence D. Stone, chief scientist at Metron Scientific Solutions which worked on the search for Flight 447 told FiveThirtyEight that he and his team joined the search for Flight 447 2 years after the plane disappeared and only after 4 other attempts to find the plane had failed but that, “Within six days, they found the wreck, and helped to show that the crash likely occurred because of pilot error in response to autopilot mode disengaging.”
It sounds like whoever is co-ordinating Australia’s P-3 Orions searching the Indian Ocean and the search more broadly might like to get Mr Stone on the Phone.
You can read more here
Business Insider Emails & Alerts
Site highlights each day to your inbox.