MAUP sensitivity analysis of ecological bias in health studies

Swift, A.D.; Liu, Lin; Uber, James G.

doi:10.1007/s10708-013-9504-z

Cited by 24 publications

(27 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The importance of the MAUP is well-recognized in health studies that use aggregate summary data to make inference on individual-level relationships between variables (e.g., Best et al 2001;Cockings and Martin 2005;Schuurman et al 2007;Swift, Liu, and Uber 2008;Diez-Roux and Mair 2010;Parenteau and Sawada 2011;Swift, Liu, and Uber 2014), and in many other fields, including political studies (Johnston et al 2004), transport modeling (Mitra and Buliung 2012), the social sciences (Manley, Flowerdew, and Steel 2006), social and economic geography (Moon and Barnett 2003;Briant, Combes, and Lafourcade 2010), econometrics (e.g., Arbia and Petrarca 2011), and agricultural applications (Nelson 2001). The scale effect (see e.g., Dungan et al 2002) has been widely studied in the fields of spatial epidemiology, geography, and the social sciences (e.g., Richardson, St€ ucker, and H emon 1987;Amrhein 1995;Wong 1996;Tate and Atkinson 2001;Gotway and Young 2002;Greenland 2002;Steel, Tranmer, and Holt 2003;Wakefield 2004;Schuurman et al 2007).…”

Section: Introductionmentioning

confidence: 99%

Empirical Zoning Distributions for Small Area Data

Burden

Steel

2016

Geographical Analysis

View full text Add to dashboard Cite

It is well established that using data summaries for a set of geographic areas or zones to estimate the parameters of a statistical model, commonly called ecological inference, frequently leads to the modifiable area unit problem (MAUP). In this article, the zoning effect of the MAUP is investigated for a range of scales. A zoning distribution is defined, and then used to characterize the zoning effect for parameter estimates from ecological analyses. Zone‐independent parameter estimates are obtained using the mean of the zoning distribution, and assessed using the variance of the zoning distribution. Zoning distributions are illustrated for parameter estimates from two ecological regression models at multiple scales using Australian National Health Survey data. For both a continuous response variable and a binary response variable, the empirical zoning distributions are unimodal, relatively symmetrical with appreciable variation, even when based on a large number of zones. The “ecological mean,” or expected value of the empirical zoning distribution at each scale, displays systematic variation with scale and the zoning distribution variance also depends on scale. The results demonstrate that the zoning effect should not be ignored, and the sensitivity of ecological analysis results to the analysis zones should be assessed.

show abstract

Section: Introductionmentioning

confidence: 99%

Empirical Zoning Distributions for Small Area Data

Burden

Steel

2016

Geographical Analysis

View full text Add to dashboard Cite

show abstract

“…However, such aggregation may result in a modifiable areal unit problem (MAUP), according to which different strength of statistical association may emerge from the analysis of data based on different units of spatial resolution (Openshaw 1984;Portnov et al 2009;Swift et al 2014). An additional problem may also arise if the events of interest are highly concentrated in space, and the overall number of areal units, available for aggregation is small, leading to inconclusive results and low statistical power (Li and Lian 2010;Zusman et al 2012).…”

Section: Introductionmentioning

confidence: 99%

Application of the double kernel density approach to the multivariate analysis of attributeless event point datasets

Zusman

Broitman

Portnov

2015

Lett Spat Resour Sci

View full text Add to dashboard Cite

Attributeless event point datasets (AEPDs) are datasets composed of discrete events or observations defined by their geographical location only and lacking any other additional attributes. Examples of such datasets include spotted criminal events, road accidents and residential locations of disease patients. A commonly used approach to the analysis of such datasets involves their aggregation into predefined areal units, such as neighborhoods or census tracts. However, this approach does not perform effectively when the events of interests are geographically localized and the number of areal units available for aggregation is small. An alternative approach to the analysis of AEPDs is based on double kernel density (DKD) smoothing, according to which events of interest are transformed into continuous density surfaces and then normalized by the density of the entire population from which the events of interest are drawn. In the present study, the applicability of the DKD approach to multivariate analysis is tested for estimation consistency, sensitivity to the number of input observations and potential bias attributed to the spatial dependency of neighboring observations. Our analysis indicates that the DKD approach provides reasonably stable and consistent estimates, if the following three preconditions are met: (a) the kernel estimation parameters are properly defined, (b) the number of reference points, used for transformation of continuous DKD surfaces into discrete observations, is sufficiently large, and (c) the spatial dependency of neighboring observations is taken into account using spatial analysis tools.

show abstract

“…24 MAUP is closely related to the ecological inference fallacy, a misinterpretation of 25 statistical inferences drawn at the group level but interpreted at the individuals 26 level [11]. With spatial data becoming a staple in a diversity of fields, the effects of 27 MAUP are explored broadle, from ecology to remote sensing and from physical 28 geography to economy [3,10,[12][13][14][15][16][17][18]. Despite the impact of MAUP is often ingnored [5], 29 when it is addressed researchers mostly assess its effect on upscaling, or 30 aggregating [3,16,18], rather than on downscaling, or disaggregating.…”

mentioning

confidence: 99%

“…On average, 199 duck models showed higher downscaling precision and higher accuracy and precision 200 compared to chickens. Swift, Liu and Uber [47] and Swift et al [14] reported that a 201 spatially clustered phenomenon aggregated using various size and shapes of areal units 202 is less affected by MAUP compared to a randomly distributed phenomenon. Because of 203 that, when the clustered structure of the observed point pattern is preserved, MAUP 204 bias is considerably reduced.…”

mentioning

confidence: 99%

“…Because of 203 that, when the clustered structure of the observed point pattern is preserved, MAUP 204 bias is considerably reduced. Moreover, Swift et al [14] also showed that aggregating 205 the independent variable using an areal unit shape related to its spatial structure reduce 206 the effect of MAUP, in their case it worked for simulated data only. To aggregate 207 empirical data, choosing a priori areal unit shape that preserves the spatial structure 208 and reduces the MAUP may be challenging, and in the context of data disaggregation, 209 may be impossible.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Downscaling livestock census data using multivariate predictive models: sensitivity to modifiable areal unit problem

Gilbert

Chaiban

et al. 2019

Preprint

View full text Add to dashboard Cite

The analysis of census data aggregated by administrative units introduces a statistical bias known as the modifiable areal unit problem (MAUP). Previous researches have mostly assessed the effect of MAUP on upscaling models. The present study contributes to clarify the effects of MAUP on the downscaling methodologies, highlighting how a priori scales and shapes choices could influence the results. We aggregated chicken and duck fine-resolution census in Thailand, using three administrative census levels in regular and irregular shapes. We then disaggregated the data within the Gridded Livestock of the World analytical framework, sampling predictors in two different ways. A sensitivity analysis on Pearson's r correlation statistics and RMSE were carried out to understand how size and shapes of the response variables affect the goodness-of-fit and downscaling performances. We showed that scale, rather than shapes and sampling methods, affected downscaling precision, suggesting that training the model using the finest administrative level available is preferable. Moreover, datasets showing non-homogeneus distribution but instead spatial clustering seemed less affected by MAUP, yielding higher Pearson's r values and lower RMSE compared to a more spatially homogenous dataset. Implementing aggregation sensitivity analysis in spatial studies could help to interpret complex results and disseminate robust products.

show abstract

MAUP sensitivity analysis of ecological bias in health studies

Cited by 24 publications

References 49 publications

Empirical Zoning Distributions for Small Area Data

Empirical Zoning Distributions for Small Area Data

Application of the double kernel density approach to the multivariate analysis of attributeless event point datasets

Downscaling livestock census data using multivariate predictive models: sensitivity to modifiable areal unit problem

Contact Info

Product

Resources

About