Spatial weighting improves accuracy in small-area demographic forecasts of urban census tract populations

Baker, Jack; Alcántara, Adélamar; Ruan, Xiaomin; Watkins, Kendra; Vasan, Srini

doi:10.1007/s12546-014-9137-1

Cited by 14 publications

(16 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For multiscale measures then, the method used to aggregate populations at small scales could be important. In the absence of publicly available individual-level data on race, there are a wide range of methods capable of allocating populations to small areas and an extensive literature covering these techniques (Baker et al., 2014; Leyk et al., 2013, 2010). Nevertheless, the implications of these aggregation choices have not yet been explored for multiscale segregation measures.…”

Section: Introduction: Segregation and The Significance Of Multiscalementioning

confidence: 99%

Key assumptions in multiscale segregation measures: How zoning and strength of spatial association condition outcomes

Fowler

2018

Environment and Planning B: Urban Analytics and City Science

View full text Add to dashboard Cite

Multiscale segregation measures have the potential to increase understanding of residential context and ultimately a wide range of social and spatial processes. By examining segregation at multiple scales, we have the opportunity to study it as more than the outcome of a single process or a measure describing a single contextual effect. Multiscale segregation encourages us to look for sorting processes and contextual effects operating at different scales and potentially even with different meanings. However, the complexity of multiscale measures introduces significant uncertainty about the role of underlying data and assumptions in producing observed outcomes, particularly at fine geographic scales. While traditional measures of segregation have been exposed to decades of scrutiny, multiscale measures are still relatively novel and less well understood. The theoretical contribution of this paper is to consider the implications of segregation as both an outcome and signifier of sorting processes at multiple scales. The empirical contribution is to consider how zoning and the degree of spatial association shape outcomes expressed as multiscale segregation measures. I examine the effects of different allocation strategies for measuring population at small scales by comparing four delineation methods. I find that the method chosen for allocating population to small areas matters, but that by the time observation units reach about 700 m2 most of the difference between methods has washed out. I also test the effect of changing the degree of assumed spatial association in generating multiscale segregation measures. I find that, as suggested by Reardon and O'Sullivan in their original exposition of their spatial segregation measure, this assumption has a relatively small effect on outcomes and is unlikely to shape substantive findings.

show abstract

Section: Introduction: Segregation and The Significance Of Multiscalementioning

confidence: 99%

Key assumptions in multiscale segregation measures: How zoning and strength of spatial association condition outcomes

Fowler

2018

Environment and Planning B: Urban Analytics and City Science

View full text Add to dashboard Cite

show abstract

“…Swanson et al (2010) used it to forecast the populations of census tracts and block groups, adjusting cohort change ratios to match population estimates early in the forecast horizon, and applying ceiling and floor limits to prevent growth becoming too high or too negative. Baker et al (2014) used it to project the populations of urban census tracts with spatial weighting applied to preliminary forecasts. This was implemented by averaging preliminary forecasts for each census tract with those of its neighbours as defined by rook and queen contiguity matrices.…”

Section: Simplified Cohort-component Methodsmentioning

confidence: 99%

“…Other researchers have applied spatial weighting to the results of population forecasts or to input assumptions. Baker et al (2014) created three sets of census tract forecasts using the Hamilton-Perry model, two which used initial projections for each census tract averaged with those of its neighbours. This approach yielded lower errors than not applying spatial averaging.…”

Section: Incorporating Socio-economic Variables and Spatial Relationshipsmentioning

confidence: 99%

“…The housing-unit model regularly proves a useful tool for researchers, often in combination with other models. As noted earlier, Baker et al (2014) used it for census tract population forecasts, employing a logistic curve to model the growth of dwellings, while Hauer et al (2015) used it for sub-county area forecasts, applying a Linear/Exponential model to forecast dwelling numbers. The housing-unit model is also regularly used by government, academic, and private sector demographers to produce local and small area population forecasts (e.g., Portland State University Population Research Center, 2015; QGSO, 2018).…”

Section: Linking Population With Housingmentioning

confidence: 99%

See 1 more Smart Citation

Methods for small area population forecasts: state-of-the-art and research needs

Wilson¹,

Grossman²,

Alexander³

et al. 2021

Preprint

View full text Add to dashboard Cite

Small area population forecasts are widely used by government and business for a variety of planning, research and policy purposes, and often influence major investment decisions. Yet the toolbox of small area population forecasting methods and techniques is modest relative to that for national and large subnational regional forecasting. In this paper we assess the current state of small area population forecasting, and suggest areas for further research. The paper provides a review of the literature on small area population forecasting methods published over the period 2001-2020. The key themes covered by the review are: extrapolative and comparative methods, simplified cohort-component methods, model averaging and combining, incorporating socio-economic variables and spatial relationships, ‘downscaling’ and disaggregation approaches, linking population with housing, estimating and projecting small area component input data, microsimulation, machine learning, and forecast uncertainty. Several avenues for further research are then suggested, including more work on model averaging and combining, developing new forecasting methods for situations which current models cannot handle, quantifying uncertainty, exploring methodologies such as machine learning and spatial statistics, creating user-friendly tools for practitioners, and understanding more about how forecasts are used.

show abstract

“…Consequently, the H-P method requires much less time and resources to implement than the CCM. Not surprisingly, it has mainly been used for subcounty geographic areas where fertility, mortality, and migration data are non-existent, unreliable, or difficult to obtain (Baker et al 2014;Smith et al 2013, p. 176;Swanson et al 2010). This method has also gained acceptance as research has demonstrated its practical value and reasonable error levels in forecasting populations (Baker et al 2017, Chapter 4;Kodiko 2014;Smith and Shahidullah 1995;Smith and Tayman 2003;Swanson and Tayman 2017).…”

Section: Introductionmentioning

confidence: 99%

Using Synthetic Adjustments and Controlling to Improve County Population Forecasts from the Hamilton–Perry Method

Tayman

Swanson

Baker³

2021

Popul Res Policy Rev

Self Cite

View full text Add to dashboard Cite

Tayman and Swanson (J Popul Res 34(3):209–231, 2017) found in Washington State counties that a forecast based on the Hamilton–Perry method using a synthetic adjustment (SYN) of cohort change ratios and child-woman ratios had greater accuracy and less bias compared to forecasts holding these ratios constant (CONST). In this paper, we assess the robustness of SYN’s efficacy by evaluating forecast accuracy, bias, and distributional error across age groups in counties nationwide. We also investigate whether forecast errors and their patterns change for SYN and CONST if forecasts by age and gender are adjusted to an independent total population forecast for each county. Our main findings are as follows: (1) SYN lowers forecast error compared to CONST whether the forecasts are controlled or not; (2) controlling also leads to the improvements in forecast error, often exceeding those in SYN; and (3) using SYN and controlling together has the greatest effect in reducing forecast error. These findings remain after controlling for population size and growth rate, but the positive impacts on forecast error of SYN and controlling are most evident in counties with less than 30,000 population and that grow by 15% or more.

show abstract

Spatial weighting improves accuracy in small-area demographic forecasts of urban census tract populations

Cited by 14 publications

References 52 publications

Key assumptions in multiscale segregation measures: How zoning and strength of spatial association condition outcomes

Key assumptions in multiscale segregation measures: How zoning and strength of spatial association condition outcomes

Methods for small area population forecasts: state-of-the-art and research needs

Using Synthetic Adjustments and Controlling to Improve County Population Forecasts from the Hamilton–Perry Method

Contact Info

Product

Resources

About