474
Views
0
CrossRef citations to date
0
Altmetric
Articles

Significance Assessment in the Application of Spatial Analytics

ORCID Icon
Pages 1740-1755 | Received 21 May 2020, Accepted 22 Oct 2020, Published online: 24 Feb 2021
 

Abstract

The breadth of spatial analytics relied on in geography is remarkable. These methods are used to gain insight, typically in the context of planning, management, decision making, and policymaking. The challenge is invariably establishing meaning in obtained findings, providing insights and knowledge. This is done, however, in very different ways depending on the spatial analytic approach, with statistical notions of significance a prevailing tool in assessment. This article reviews significance assessment approaches in the application of spatial analytics. Noteworthy in this review is that many approaches can be considered through the lens of sampling. In some cases, the underlying sample is a few or as small as one. There are methods, however, that are based on sampling that is comprehensive, involving an implicit or explicit enumeration of all possible outcomes. This suggests that significance assessment using certain methods accounts for the entire range of possibilities, whereas other methods draw inference from scant sampling. In addition to the sampling perspective, extrapolation as well as indirect accuracy and anecdotal measures of assessment are not uncommon. The comparative review of spatial analytic methods suggests that significance is assessed in many different ways, making meaning interpretation challenging.

地理学依赖空间分析的广度是惊人的。在规划、管理、决策和制定政策时,我们采用空间分析获得认知。挑战是对结果的解读、提供认知和知识。然而,不同的空间分析方法,其手段也不同,评估的主要方法是统计概念上的显著性。本文综述了空间分析应用中的显著性评估方法。值得注意的是,许多方法可以从采样角度来考虑。某些情况下,样本数很少,甚至只有一个。而有些方法是基于全面采样的,明确地或者隐性地枚举了所有可能结果。这表明,某些方法的显著性评估可以解释整个概率空间,而其它方法则基于小采样进行推理。除了采样,外推法以及准确度和轶事的间接评估方法并不少见。对空间分析方法的比较研究表明,显著性评估有很多不同方式,使得含义的解读具有挑战性。

Es notable el grado con el que la analítica espacial depende de la geografía. Estos métodos se usan para ganar perspicacia, típicamente en los contextos de planificación, administración, toma de decisiones y políticas públicas. Invariablemente, el método consiste en establecer significado en los resultados logrados, proporcionando nuevas perspectivas y conocimiento. Esto se hace, sin embargo, de maneras muy diferentes según el enfoque de la analítica espacial, siendo las nociones estadísticas de significancia la herramienta dominante de evaluación. Este artículo revisa los enfoques de evaluación de la significancia en la aplicación de la analítica espacial. Digno de destacar en esta revisión es el hecho de que muchos enfoques pueden ser considerados a través de la lente del muestreo. En ciertos casos, la muestra que los subraya es de unos pocos, o tan pequeña como una unidad. Sin embargo, hay métodos que se basan en una muestra que es lo suficientemente amplia para involucrar una enumeración implícita o explícita de todos los resultados posibles. Esto sugiere que la evaluación de la significancia que usa ciertos métodos explica la gama total de posibilidades, mientras que otros métodos deducen la inferencia desde un muestreo limitado. Además de la perspectiva del muestreo, la extrapolación, lo mismo que la exactitud indirecta y las medidas anecdóticas de evaluación, no son raras. La revisión comparativa de los métodos de la analítica espacial sugiere que la significancia es evaluada de muchas maneras diferentes, lo que determina que la interpretación del significado sea todo un reto.

Notes

1 Merriam-Webster defines meaningful as “having a meaning or purpose; full of meaning; significant.” Merriam-Webster, s.v. “meaningful,” accessed February 10, 2021, https://www.merriam-webster.com/dictionary/meaningful.

2 Merriam-Webster, s.v. “significance,” accessed February 10, 2021, https://www.merriam-webster.com/dictionary/significance.

3 There are exceptions. For example, Lagrangian relaxation is a method that can be used in both an exact way and as a heuristic. Specifically, if Lagrangian relaxation is used to solve an integer program and is embedded within a branch and bound routine, it would be considered exact under conditions of bound convergence to zero. If not embedded within branch and bound, it would be a heuristic approach with an associated valid bound that might or might not be useful, depending on convergence, optimality gap, problem context, and so on.

Additional information

Notes on contributors

Alan T. Murray

ALAN T. MURRAY is a Professor in the Department of Geography at University of California at Santa Barbara, Santa Barbara, CA 93106. E-mail: [email protected]. His research interests include GIScience, spatial analytics, and location modeling in addressing urban and regional planning issues, as well as environmental sustainability.

Log in via your institution

Log in to Taylor & Francis Online

PDF download + Online access

  • 48 hours access to article PDF & online version
  • Article PDF can be downloaded
  • Article PDF can be printed
USD 53.00 Add to cart

Issue Purchase

  • 30 days online access to complete issue
  • Article PDFs can be downloaded
  • Article PDFs can be printed
USD 312.00 Add to cart

* Local tax will be added as applicable

Related Research

People also read lists articles that other readers of this article have read.

Recommended articles lists articles that we recommend and is powered by our AI driven recommendation engine.

Cited by lists all citing articles based on Crossref citations.
Articles with the Crossref icon will open in a new tab.