You should not rely only on empiric methods, but as well on analysis. If you have a change of the situation, that from other analysis makes a lot of sense, that it will have an effect, an outlier is something quite different.
Or in other words. Frequentist methods sucks, compared to Baysian approaches, that figure in a priori probability densities. I take dodo's graph with the explaination any time as a evidence that the methods proposed in Hungary work.

Nevertheless:
Freie Fahrt für freie Bürger ;-p

Der Amerikaner ist die Orchidee unter den Menschen
Volker Pispers

Statistical variation depends on sample size. This is apparent on the second graph: check the lines for the Baltic countries or Luxembourg. For larger countries, you have a signal not noise.

• The large bump you see for Slovakia is the result of the April 1997 general speed limit raise (50 to 60 in cities, 110 to 130 on highways).

• In the Czech Republic, several road safety measures were implemented until 2006, when they switched to a points system, too. In 2007, the new government even talked about raising the limit on highways to 160 km/h...

• The 22% drop in the Netherlands in 2004 doesn't seem to have a single reason, but it seems a major fuel-efficient driving campaign combined with the peaking of roundabout construction that year.

• For Hungary, the next biggest change, the steep rise in 2001-2002 coincides with the introduction of the points system in an (initially) lenient form and a raise of speed limits by 10 km/h.

_{*Lunatic*, n.
One whose delusions are out of fashion.}

That was the Slovenian graph I was looking at, not the Danish...

Ah well, confirmation bias can be fun while the music is playing...

- Jake

If you only spend 20 minutes of the rest of your life on economics, go spend them here.