Integration of MNO data with survey data to produce commuting statistics

Abstract

Historically, decennial population censuses have served as the foundation for official statistics on commuter flows between municipalities. However, to obtain more timely data, Istat, the Italian National Institute for Statistics, among other statistical agencies, has transitioned to conducting annual census surveys with smaller sample sizes. This shift introduces several challenges in deriving accurate commuting statistics. The availability of Mobile Network Operator (MNO) data enables the identification of recurring flows between home and work or study locations. These flows could potentially become the primary source for generating official statistics by properly adjusting the MNO coverage in a quasi randomisation (QR) approach. In this paper, we explore the use of MNO data to estimate the number of commuters between the municipalities of an Italian region, with a focus on the quasi-randomisation approach.