Tricking your optimiser

I have found that optimisers (R’s optim to be precise) are sometime unstable. Not in a numerical sense, but in a more practical sense, i.e. choking on certain inputs (I wasn’t able to figure out when exactly) and in the end crashing, without the possibility of recovery or error-processing. Which is quite bad, when you’re in the mid of some long calculations, e.g. a Monte-Carlo experiment. I found that optim’s standard method, Nelder-Mead, was unsusceptible to such crashes (Please, geeks, explain me why!). But with Nelder-Mead, you cannot use parameter constraints, so you have to formulate your optimisation problem in an unconstrained way. Here are some of my tricks.

Continue reading Tricking your optimiser

Democracy in the time of postfacts

Some time ago, an op-ed in a German newspaper (Die Zeit, I believe) decried the use of the term „postfact“ and suggested we should call the bullshit uttered by the Trump administration, the Brexit campaign and others as just what it is: lies. Well, certainly, postfacts are lies, but there is a subtle distinction. Post-facts create their own, subjective version of reality – or “truth” – whereas lies contradict the objective truth. This distinction lays bare a fundamental problem of our democratic way to organise government. It does not really matter, whether Donald Trump or Nigel Farage actually believe the nonsense they utter, but it matters that their voters believe it, because it fits their view on the world.

Continue reading Democracy in the time of postfacts

One Swallow Doesn’t Make A Summer

Today Eurostat announced that the Euro area’s inflation rate (as measured by the HICP) has reached two per cent in February (see press release here: While seems finally some good news for the crisis-battered Euro area, it actually isn’t. Here’s why. Continue reading One Swallow Doesn’t Make A Summer