Search

Traditional methods of counting bicyclists are resource-intensive and generate data with sparse spatial and temporal detail. Previous research suggests big data from crowdsourced fitness apps offer a new source of bicycling data with high spatial and temporal resolution. However, crowdsourced bicycling data are biased as they oversample recreational riders. Our goals are to quantify geographical variables, which can help in correcting bias in crowdsourced, data and to develop a generalized method to correct bias in big crowdsourced data on bicycle ridership in different settings in order to generate maps for cities representative of all bicyclists at a street-level spatial resolution. We used street-level ridership data for 2016 from a crowdsourced fitness app (Strava), geographical covariate data, and official counts from 44 locations across Maricopa County, Arizona, USA (training data); and 60 locations from the city of Tempe, within Maricopa (test data). First, we quantified the relationship between Strava and official ridership data volumes. Second, we used a multi-step approach with variable selection using LASSO followed by Poisson regression to integrate geographical covariates, Strava, and training data to correct bias. Finally, we predicted bias-corrected average annual daily bicyclist counts for Tempe and evaluated the model’s accuracy using the test data. We found a correlation between the annual ridership data from Strava and official counts (R2 = 0.76) in Maricopa County for 2016. The significant variables for correcting bias were: The proportion of white population, median household income, traffic speed, distance to residential areas, and distance to green spaces. The model could correct bias in crowdsourced data from Strava in Tempe with 86% of road segments being predicted within a margin of ±100 average annual bicyclists. Our results indicate that it is possible to map ridership for cities at the street-level by correcting bias in crowdsourced bicycle ridership data, with access to adequate data from official count programs and geographical covariates at a comparable spatial and temporal resolution.

In 2020, Arizonans approved Proposition 207, the Smart and Safe Arizona Act, which legalized recreational marijuana sales. Previous research has typically used non‐spatial survey data to understand marijuana legalization voting patterns. However, voting behavior can, in part, be shaped by geographic context, or place, which is unaccounted for in aspatial survey data. We use multiscale geographically weighted regression to analyze how place shaped Proposition 207 voting behavior, independently of demographic variations across space. We find significant spatial variability in the sensitivity of voting for Proposition 207 to changes in several of the predictor variables of opposition and support for recreational marijuana legalization. We argue that local statistical modeling approaches provide a more in‐depth understanding of ballot measure voting behavior than the current use of global models. Related Articles: Branton, Regina, and Ronald J. McGauvran. 2018. "Mary Jane Rocks the Vote: The Impact of Climate Context on Support for Cannabis Initiatives." Politics & Policy 46(2): 209–32. https://doi.org/10.1111/polp.12248. Brekken, Katheryn C., and Vanessa M. Fenley. 2020. "Part of the Narrative: Generic News Frames in the U.S. Recreational Marijuana Policy Subsystem." Politics & Policy 49(1): 6–32. https://doi.org/10.1111/polp.12388. Fisk, Jonathan M., Joseph A. Vonasek, and Elvis Davis. 2018. "'Pot'reneurial Politics: The Budgetary Highs and Lows of Recreational Marijuana Policy Innovation." Politics & Policy 46(2): 189–208. https://doi.org/10.1111/polp.12246. [ABSTRACT FROM AUTHOR]

This report describes the results of NCGIA Research Initiative 14 on “GIS and Spatial Analysis.” This initiative focused on the interface between these spatial statistical problems and geographic information systems, a major goal being to advance the capabilities of GIS in facilitating spatial statistical analyses.

This report oultines the research agenda for NCGIA-sponsored Initiative on GIS and Spatial Analysis and summarizes the discussions of the specialist meeting held at Humphrey's Half Moon Inn in San Diego between April 15-18, 1992.

It seems widely expected that future GISs will have increased analytical capabilities that will take them beyond being efficient display and database management devices. Several attempts have already been made to link existing analytical software to various GISs. However, a problem with all of these attempts is that the user is forced to switch back and forth between the GIS operating environment and the analytical software. In this paper we present a statistical analysis package, STACAS, that runs totally within the operating environment of a GIS and utilizes a command structure that makes running the package transparent to the user of the GIS.

Fractal research seems to have permeated most, if not all, areas of research concerned with form, from the micro-level aggregation of water molecules or particles of zinc oxide to the macro analysis of the structure of landmasses and cities. Given that the study of spatial form and its links to spatial processes is one of basic research areas within Geography, it is not surprising that research on fractals can be found in many subfields of the discipline, including geomorphology, climatology, urban and regional analysis, cartography, and remote sensing.Within this working paper, we provide a sample of the growing literature in this area. The emphasis is on references that have appeared in the published literature. The bibliography is arranged in three sections: general references; measurement issues; and applications.

The optimal bandwidths produced in the calibration of MGWR models have uncertainty attached to them which can be quantified and a confidence interval placed around each covariate-specific bandwidth. Without data standardization, the optimized covariate-specific bandwidths will be, in part, a function of the data variability and to ensure comparability across bandwidths it is therefore important to make the variability of each covariate the same. The first is that a current bibliography (Fotheringham et al., [7]) lists over 2,500 references for applications of Geographically Weighted Regression (GWR) and Multiscale Geographically Weighted Regression (MGWR) divided into 30 categories so this is clearly a popular research area. GWR is simply MGWR with the unrealistic restriction that the bandwidth is the same for each process being modeled and also for the local intercept. [Extracted from the article]

Studies of spatially varying parameter estimates obtained in the calibration of various types of local statistical models are commonplace. The variation in such estimates is typically explained in terms of spatially varying processes. This paper highlights that an alternative explanation for spatially varying parameter estimates, in terms of non‐linearity, should be examined prior to relating such variation to spatially varying processes. This can be achieved by a simple screening procedure which is described and demonstrated and which can easily be applied to the results of any local model. The problem is highlighted, and the solution demonstrated, with a set of simulated data and then with a real‐world data set. The paper also highlights the obverse situation whereby the inappropriate application of a GAM produces spurious nonlinear results when the real relationships are linear but spatially varying. [ABSTRACT FROM AUTHOR]