Dataset Information

Creating local estimates from a population health survey: practical application of small area estimation methods.

ABSTRACT: Regular health surveys can produce reliable estimates at higher geographic levels but not for small areas. Alternatives are to aggregate data over several years or use model-based methods. We created and evaluated model-based estimates for four health-related outcomes by gender, for 153 Local Government Areas using data from the New South Wales Population Health Survey. The evaluation examined evidence on bias and determined the covariates available and appropriate for each outcome variable. The evaluation considered the likely precision of the resulting estimates. The bias and precision of results for single years (2006-2008) for each outcome variable using six covariate specifications were compared with direct survey estimates based on a single year's data and those obtained by aggregating over seven years. A practical issue is how to choose covariates to include in the models as the best covariate specification varies between outcome variables. Model-based results had median root mean squared errors between 3.3% and 5.5% (max 5.2% and 11.3% respectively) and median relative root mean squared errors between 6.8% and 24.5% (max 11.7% and 41.5% respectively). The model-based estimates were unbiased compared with direct estimates based on one or seven years of data and when aggregated to a point where direct estimates were reliable. The bias and reliability assessment process provides a way for policymakers to have confidence in model-based estimates.

SUBMITTER: Hindmarsh D

PROVIDER: S-EPMC7327397 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Creating local estimates from a population health survey: practical application of small area estimation methods.

Hindmarsh Diane D Steel David D

AIMS public health 20200622 2

Regular health surveys can produce reliable estimates at higher geographic levels but not for small areas. Alternatives are to aggregate data over several years or use model-based methods. We created and evaluated model-based estimates for four health-related outcomes by gender, for 153 Local Government Areas using data from the New South Wales Population Health Survey. The evaluation examined evidence on bias and determined the covariates available and appropriate for each outcome variable. The ...[more]

PMID: 32617366

Similar Datasets

Project description:BackgroundModel-based small area estimation methods can help generate parameter estimates at the district level, where planned population survey sample sizes are not large enough to support direct estimates of HIV prevalence with adequate precision. We computed district-level HIV prevalence estimates and their 95% confidence intervals for districts in Uganda.MethodsOur analysis used direct survey and model-based estimation methods, including Fay-Herriot (area-level) and Battese-Harter-Fuller (unit-level) small area models. We used regression analysis to assess for consistency in estimating HIV prevalence. We use a ratio analysis of the mean square error and the coefficient of variation of the estimates to evaluate precision. The models were applied to Uganda Population-Based HIV Impact Assessment 2016/2017 data with auxiliary information from the 2016 Lot Quality Assurance Sampling survey and antenatal care data from district health information system datasets for unit-level and area-level models, respectively.ResultsEstimates from the model-based and the direct survey methods were similar. However, direct survey estimates were unstable compared with the model-based estimates. Area-level model estimates were more stable than unit-level model estimates. The correlation between unit-level and direct survey estimates was (β1 = 0.66, r2 = 0.862), and correlation between area-level model and direct survey estimates was (β1 = 0.44, r2 = 0.698). The error associated with the estimates decreased by 37.5% and 33.1% for the unit-level and area-level models, respectively, compared to the direct survey estimates.ConclusionsAlthough the unit-level model estimates were less precise than the area-level model estimates, they were highly correlated with the direct survey estimates and had less standard error associated with estimates than the area-level model. Unit-level models provide more accurate and reliable data to support local decision-making when unit-level auxiliary information is available.

Project description:BackgroundThe scarcity of country data (e.g. a cancer registry) for the burden of cervical cancer (CC) in low-income countries (LCIs) such as Swaziland remains a huge challenge. Such data are critical to inform local decision-making regarding resource allocation [1]. We aimed to estimate likely cervical cancer incidence in Swaziland using three different methodologies (triangulation), to help better inform local policy guidance regarding likely higher "true" burden and increased resource allocation required for treatment, cervical cancer screening and HPV vaccine implementation.MethodsThree methods were applied to estimate CC incidence, namely: 1) application of age-specific CC incidence rates for Southern African region from GLOBOCAN 2012 extrapolated to the 2014 Swaziland female population; 2) a linear regression based model with transformed age-standardised CC incidence against hr-HPV (with and without HIV as a covariate) prevalence among women with normal cervical cytology; and 3) a mathematical model, using a natural history approach based on parameter estimates from various available literature and local survey estimates. We then triangulated estimates and uncertainty from the three models to estimate the most likely CC incidence rate for Swaziland in 2015.ResultsThe projected incidence estimates for models 1-3 were 69.4 (95% CI: 66.7-72.1), 62.6 per 100,000 (95%CI: 53.7-71.8) and 44.6 per 100,000 (41.5 to 52.1) respectively. Model 2 with HIV prevalence as covariate estimated a higher CC incidence rate estimate of 101.1 per 100,000 (95%CI: 90.3-112.2). The triangulated ('averaged') age-standardized CC incidence based across the 3 models for 2015 was estimated at 69.4 per 100,000 (95% CI: 63.0-77.1) in Swaziland.ConclusionIt is widely accepted that cancer incidence (and in this case CC) is underestimated in settings with poor and lacking registry data. Our findings suggest that the projected burden of CC is higher than that suggested from other sources. Local health policy decisions and decision-makers need to re-assess resource allocation to prevent and treat CC effectively, which is likely to persist given the very high burden of hr-HPV within the country.

Project description:BackgroundThe HIV/AIDS pandemic has had a very devastating impact at a global level, with the Eastern and Southern African region being the hardest hit. The considerable geographical variation in the pandemic means varying impact of the disease in different settings, requiring differentiated interventions. While information on the prevalence of HIV at regional and national levels is readily available, the burden of the disease at smaller area levels, where health services are organized and delivered, is not well documented. This affects the targeting of HIV resources. There is need, therefore, for studies to estimate HIV prevalence at appropriate levels to improve HIV-related planning and resource allocation.MethodsWe estimated the district-level prevalence of HIV using Small-Area Estimation (SAE) technique by utilizing the 2016 Zambia Population-Based HIV Impact Assessment Survey (ZAMPHIA) data and auxiliary data from the 2010 Zambian Census of Population and Housing and the HIV sentinel surveillance data from selected antenatal care clinics (ANC). SAE models were fitted in R Programming to ascertain the best HIV predicting model. We then used the Fay-Herriot (FH) model to obtain weighted, more precise and reliable HIV prevalence for all the districts.ResultsThe results revealed variations in the district HIV prevalence in Zambia, with the prevalence ranging from as low as 4.2% to as high as 23.5%. Approximately 32% of the districts (n = 24) had HIV prevalence above the national average, with one district having almost twice as much prevalence as the national level. Some rural districts have very high HIV prevalence rates.ConclusionsHIV prevalence in Zambian is highest in districts located near international borders, along the main transit routes and adjacent to other districts with very high prevalence. The variations in the burden of HIV across districts in Zambia point to the need for a differentiated approach in HIV programming within the country. HIV resources need to be prioritized toward districts with high population mobility.

Project description:CONTEXT:The Public Health Workforce Interests and Needs Survey (PH WINS) was first fielded in 2014 and is the largest public health workforce survey in the nation. This article elucidates the methods used for the 2017 PH WINS fielding. PROGRAM OR POLICY:PH WINS was fielded to a nationally representative sample of State Health Agency Central Office (SHA-CO) staff, as well as local health department (LHD) staff. The instrument largely mirrored 2014, though the training needs section was revised, and a validated item measuring burnout in staff was added. IMPLEMENTATION:Staff lists were collected directly from all participating state and local agencies. Forty-seven state health agencies (SHAs), 26 large LHDs, and 71 midsize LHDs participated. All SHAs were surveyed using a census approach. The nationally representative SHA-CO frame is representative of all central office staff members. The nationally representative local frame was a complex survey design, wherein staff from LHDs were randomly sampled across 20 strata, based on agency size and geographic region. Staff were also contributed with certainty from large LHDs in nondecentralized states. The frame is representative of staff at LHDs serving more than 25 000 people and with 25 or more staff members. Other LHDs are excluded, and so PH WINS is not representative of smaller LHDs. Balanced repeated replication weights were used to adjust variance estimates for the complex design. EVALUATION:Overall, 47 604 people responded to PH WINS in 2017 across all frames. PH WINS 2017 achieved a response rate of 48%. The design effect for the SHA-CO frame was 1.46 and was 16.42 for the local frame. DISCUSSION:PH WINS now offers a nationally representative sample of both SHA-CO and LHD staff across 4 major domains: workplace environment, training needs, emerging concepts in public health, and demographics. Both practice and academia can use PH WINS to better understand the perceptions and needs of staff, address training gaps, and work to recruit and retain quality staff.

Dataset Information

Creating local estimates from a population health survey: practical application of small area estimation methods.

Publications

Creating local estimates from a population health survey: practical application of small area estimation methods.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets