Deeper Spatial Statistical Insights into Small Geographic Area Data Uncertainty - PubMed (original) (raw)

Deeper Spatial Statistical Insights into Small Geographic Area Data Uncertainty

Daniel A Griffith et al. Int J Environ Res Public Health. 2020.

Abstract

Small areas refer to small geographic areas, a more literal meaning of the phrase, as well as small domains (e.g., small sub-populations), a more figurative meaning of the phrase. With post-stratification, even with big data, either case can encounter the problem of small local sample sizes, which tend to inflate local uncertainty and undermine otherwise sound statistical analyses. This condition is the opposite of that afflicting statistical significance in the context of big data. These two definitions can also occur jointly, such as during the standardization of data: small geographic units may contain small populations, which in turn have small counts in various age cohorts. Accordingly, big spatial data can become not-so-big spatial data after post-stratification by geography and, for example, by age cohorts. This situation can be ameliorated to some degree by the large volume of and high velocity of big spatial data. However, the variety of any big spatial data may well exacerbate this situation, compromising veracity in terms of bias, noise, and abnormalities in these data. The purpose of this paper is to establish deeper insights into big spatial data with regard to their uncertainty through one of the hallmarks of georeferenced data, namely spatial autocorrelation, coupled with small geographic areas. Impacts of interest concern the nature, degree, and mixture of spatial autocorrelation. The cancer data employed (from Florida for 2001-2010) represent a data category that is beginning to enter the realm of big spatial data; its volume, velocity, and variety are increasing through the widespread use of digital medical records.

Keywords: big data; big spatial data; cancer; small area; small geographic area.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1

Figure 1

Histograms for random samples from a continuous uniform distribution. Sample size n: left—10,000; middle—100,000; right—1,000,000. Bin size: top—0.1; middle—0.01; bottom—0.001.

Figure 2

Figure 2

The State of Florida, and the locations of the six studied metropolitan statistical areas (MSAs).

Figure 3

Figure 3

Scatterplots of reference population distributions, ages 20+. Left (a): paired by age cohorts; black denotes male, grey denotes female. Right (b): ordered by age cohorts; blue denotes World, red denotes US, and green denotes Florida (FL).

Figure 4

Figure 4

Scatterplots of crude cancer rates (vertical axis) versus age-and sex-adjusted cancer rates (horizontal axis); blue denotes World, red denotes US, and green denotes Florida (FL). (A). Top to bottom: cancer type (female breast, colorectal, lung & bronchus, melanoma skin, urinary bladder). Left to right: MSA (Jacksonville, Miami, Orland). (B). Top to bottom: cancer type (female breast, colorectal, lung & bronchus, melanoma skin, urinary bladder). Left to right: MSA Pensacola, Tallahassee, Tampa).

Figure 4

Figure 4

Scatterplots of crude cancer rates (vertical axis) versus age-and sex-adjusted cancer rates (horizontal axis); blue denotes World, red denotes US, and green denotes Florida (FL). (A). Top to bottom: cancer type (female breast, colorectal, lung & bronchus, melanoma skin, urinary bladder). Left to right: MSA (Jacksonville, Miami, Orland). (B). Top to bottom: cancer type (female breast, colorectal, lung & bronchus, melanoma skin, urinary bladder). Left to right: MSA Pensacola, Tallahassee, Tampa).

Similar articles

Cited by

References

    1. Jenish N., Prucha I. Central Limit Theorems and Uniform Laws of Large Numbers for arrays of random fields. J. Econom. 2009;150:86–98. doi: 10.1016/j.jeconom.2009.02.009. - DOI - PMC - PubMed
    1. De Mauro A., Greco M., Grimaldi M. A formal definition of big data based on its essential features. Libr. Rev. 2016;65:122–135. doi: 10.1108/LR-06-2015-0061. - DOI
    1. Jensen R., Griffith D., Monmonier M., De Gloria S., Herrington L., McMaster R., Can A. Final Report: New York State Program in Geographic Information and Analysis. Department of Geography, Syracuse University; Syracuse, NY, USA: 1990.
    1. Cressie N., Olsen A., Cook D. Massive data sets: Problems and possibilities, with applications to environmental monitoring. In: Committee on Applied and Theoretical Statistics; Board of Mathematical Sciences; National Research Council, editor. Massive Data Sets: Proceedings of a Workshop. National Academy Press; Washington, DC, USA: 1996. pp. 115–119.
    1. Ellis P. The Essential Guide to Effect Sizes: Statistical Power, Meta-Analysis, and the Interpretation of Research Results. Cambridge University Press; New York, NY, USA: 2010.

Publication types

MeSH terms

LinkOut - more resources