The summer is the so-called “silly season” – the time when media (and the public?) descend into the mental equivalent of a slumber.

It is therefore not so surprising that the talk of the town where I’m vacationing – Portugal – is less concerned with the fallout of Brexit and the shifting balance of powers and alliances between the USA, Europe, and China or Russia, and much more about whether Madonna’s moving to Portugal and her social media presence has important benefits for Portuguese tourism. 

For those of you less familiar with Madonna’s life, she moved to Lisbon, Portugal, in May 2017 (since a much heralded boon for Portuguese tourism) and was able to extract some (but less popular) benefits from Lisbon’s local government, including a welcoming reception by Lisbon’s Mayor and deal for a number of parking spots in the old town for her fleet of 15 automobiles. 

One popular Portuguese satirical commentary show, Governo Sombra (Shadow Government), has called for scientific studies showing the economic benefits of Madonna’s move to Portugal. 

I have taken up this challenge by analysing the official statistics on the number of overnight stays that are made available by the Instituto Nacional de Estatística (INE; Statistics Portugal). Specifically, I used the time series data between January 2006 and April 2017 to forecast the results for the post-Madonna period of May 2017 to April 2018 (unfortunately INE doesn’t yet provide more recent data). My rationale for this analysis is that an increase of overnight stays after Madonna’s arrival that goes beyond the forecast based on the pre-Madonna period would represent supporting evidence for Madonna’s positive effect on Portuguese tourism. Alas, I am able to report that the data do not reveal a Madonna effect. As one can see in the figure below the actual number of overnight stays falls well within the predicted confidence intervals from the simple forecast model. 

Of course, there are a number of problems with this type of analysis as has been pointed out by Campbell and Ross (1968). Perhaps a good summer reading as a break from the silliness of the season. 

Campbell, D. T., Ross, H. L. (1968). The Connecticut crackdown on speeding: Time-series data in quasi-experimental analysis. Law and Society Review, 3(1), 33. http://doi.org/10.2307/3052794