Intensity-Based Location Sampling Method For Investigating Socio-Economic Challenges : Ensuring External Validity In Surveys of Unknown Populations

Abstract

Timely, representative evidence on users of public spaces and emergent venues is essential for diagnosing and addressing socioeconomic challenges. The Intensity-Based Location Sampling (ILS) method was developed to ensure the representativeness of populations without a prior sampling frame; its essence is the synchronous integration of real-time traffic counts with probability-based intercept surveys, allocating interviews in proportion to observed population density across zones (and, in its extension, across times). Compared with classic location or time-location sampling, external validity is strengthened, length-biased selection is reduced, and representative samples can be produced without a prior sampling frame. Scientific novelty lies in coupling counting and interviewing in real time and in an allocation rule that minimizes the discrepancy between survey and population intensities, distinguishing the approach from existing designs. The effectiveness of ILS is demonstrated on statistical data from a public urban park in Budapest, Hungary (2021): face-to-face interviews with N = 253 park visitors (embedded in a broader N = 1000 survey), with real-time traffic counts in nine zones and dynamic reallocation of fieldworkers to undersampled areas. The resulting ILS fit index (0.0179) indicated close correspondence between survey and observed distributions. These results illustrate how ILS can generate actionable, weighting-free evidence for planners and policy-makers, ensuring that interventions respond to real patterns of use and need. Beyond parks, the method is adaptable to transport hubs, markets, festivals, and crisis contexts, offering a scalable and cost-effective tool for socioeconomic research where populations are hidden, mobile, or undefined. By extending ILS with an explicit temporal component (ITLS – Intensity Based Time and Location Sampling), further prospects are opened for rigorous, low-cost study of socio-economic challenges in hidden, mobile, or otherwise undefined populations.