Statistical Modelling of Pedestrian Flows

Abstract

Pedestrian counts and in particular their relation to the buildings in the vicinity of the streetandtothestructureofthestreetnetworkisofcentralinterestinthespacesyntax field. This report is concerned with using statistical techniques to model pedestrian countsandinparticularhowthesecountsvaryovertheday. Ofinterestiswhetherthe variationoverthedayforastreetcanbepredictedbasedonitsdensity type,describing the nearby buildings, and street type, describing its role in in the city’s overall street network. UsingdatafromAmsterdam,LondonandStockholmthehour-by-hourpedestriancounts are modelled with the so-called functional ANOVA method, using the aforementioned typestodividethestreetsintogroups.Additionally,theeffectofthepresenceofschools, storesandpublictransportstopsnearthestreetsonpedestriancountsisconsidered.The modelisfittedinaBayesianframeworkusingthe integrated nested Laplace approximation technique. The results indicate that this model works well but that it might be somewhat too rigid to capture all the variability in the data, failing to capture some of the differencebetween groupsand between thecities. Somepossible extensionsto the modeltoremedythisaresuggested.