Dataset Information

Is there much variation in variation? Revisiting statistics of small area variation in health services research.

ABSTRACT: BACKGROUND: The importance of Small Area Variation Analysis for policy-making contrasts with the scarcity of work on the validity of the statistics used in these studies. Our study aims at 1) determining whether variation in utilization rates between health areas is higher than would be expected by chance, 2) estimating the statistical power of the variation statistics; and 3) evaluating the ability of different statistics to compare the variability among different procedures regardless of their rates. METHODS: Parametric bootstrap techniques were used to derive the empirical distribution for each statistic under the hypothesis of homogeneity across areas. Non-parametric procedures were used to analyze the empirical distribution for the observed statistics and compare the results in six situations (low/medium/high utilization rates and low/high variability). A small scale simulation study was conducted to assess the capacity of each statistic to discriminate between different scenarios with different degrees of variation. RESULTS: Bootstrap techniques proved to be good at quantifying the difference between the null hypothesis and the variation observed in each situation, and to construct reliable tests and confidence intervals for each of the variation statistics analyzed. Although the good performance of Systematic Component of Variation (SCV), Empirical Bayes (EB) statistic shows better behaviour under the null hypothesis, it is able to detect variability if present, it is not influenced by the procedure rate and it is best able to discriminate between different degrees of heterogeneity. CONCLUSION: The EB statistics seems to be a good alternative to more conventional statistics used in small-area variation analysis in health service research because of its robustness.

SUBMITTER: Ibanez B

PROVIDER: S-EPMC2676262 | biostudies-other | 2009

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Is there much variation in variation? Revisiting statistics of small area variation in health services research.

Ibáñez Berta B Librero Julián J Bernal-Delgado Enrique E Peiró Salvador S López-Valcarcel Beatriz González BG Martínez Natalia N Aizpuru Felipe F

BMC health services research 20090402

<h4>Background</h4>The importance of Small Area Variation Analysis for policy-making contrasts with the scarcity of work on the validity of the statistics used in these studies. Our study aims at 1) determining whether variation in utilization rates between health areas is higher than would be expected by chance, 2) estimating the statistical power of the variation statistics; and 3) evaluating the ability of different statistics to compare the variability among different procedures regardless o ...[more]

PMID: 19341469

Similar Datasets

Project description:ObjectiveTo describe, qualitatively and quantitatively, the impact of a review by multiple institutional review boards (IRBs) on the conduct of a multisite observational health services research study. DATA SOURCE AND SETTING: Primary data collection during 2002, 2003, and 2004 at 43 United States Department of Veterans Affairs (VA) primary care clinics.DesignExplanatory sequential mixed methods design incorporating qualitative and quantitative elements in sequence. DATA COLLECTION AND ABSTRACTION METHODS: Field notes and documents collected by research staff during a multisite observational health services research study were used in thematic analysis. Themes were quantified descriptively and merged with timeline data.Principal findingsApproximately 4,680 hours of staff time over a 19-month period were devoted solely to the IRB process. Four categories of phenomena impacting research were observed: (1) Recruitment, retention, and communication issues with local site principal investigators (PIs). Local PIs had no real role but were required by IRBs. Twenty-one percent of sites experienced turnover in local PIs, and local PI issues added significant delay to most sites. (2) Wide variation in standards applied to review and approval of IRB applications. The study was designed to be qualified under U.S. government regulations for expedited review. One site exempted it from review (although it did not qualify for exemption), 10 granted expedited review, 31 required full review, and one rejected it as being too risky to be permitted. Twenty-three required inapplicable sections in the consent form and five required HIPAA (Health Insurance Portability and Accountability Act of 1996) consent from physicians although no health information was asked of them. Twelve sites requested, and two insisted upon, provisions that directly increased the risk to participants. (3) Multiple returns for revision of IRB applications, consent documents, and ancillary forms. Seventy-six percent of sites required at least one resubmission, and 15 percent of sites required three or more (up to six) resubmissions. Only 12 percent of sites required any procedural or substantive revision; most resubmissions were editorial changes to the wording of the consent document. (4) Process failures (long turnaround times, lost paperwork, difficulty in obtaining necessary forms, unavailability of key personnel at IRBs). The process required from 52 to 798 (median 286) days to obtain approval at each site.ConclusionsSeveral features of the IRB system as currently configured impose costly burdens of administrative activity and delay on observational health services research studies, and paradoxically decrease protection of human subjects. Central review with local opt-out, cooperative review, or a system of peer review could reduce costs and improve protection of human subjects.

Project description:ObjectiveEngaging stakeholders in reviews is considered to generate more relevant evidence and to facilitate dissemination and use. As little is known about stakeholder involvement, we assessed the characteristics of their engagement in systematic and rapid reviews and the methodological quality of included studies. Stakeholders were people with a particular interest in the research topic.DesignMethodological review.Search strategyFour databases (Medline, Embase, Cochrane database of systematic reviews, databases of the University of York, Center for Reviews and Dissemination (CRD)) were searched based on an a priori protocol. Four types of reviews (Cochrane and non-Cochrane systematic reviews, rapid and CRD rapid reviews) were retrieved between January 2011 and October 2015, pooled by potential review type and duplicates excluded. Articles were randomly ordered and screened for inclusion and exclusion criteria until 30 reviews per group were reached. Their methodological quality was assessed using AMSTAR and stakeholder characteristics were collected.ResultsIn total, 57 822 deduplicated citations were detected with potential non-Cochrane systematic reviews being the biggest group (56 986 records). We found stakeholder involvement in 13% (4/30) of Cochrane, 20% (6/30) of non-Cochrane, 43% (13/30) of rapid and 93% (28/30) of CRD reviews. Overall, 33% (17/51) of the responding contact authors mentioned positive effects of stakeholder involvement. A conflict of interest statement remained unmentioned in 40% (12/30) of non-Cochrane and in 27% (8/30) of rapid reviews, but not in Cochrane or CRD reviews. At most, half of non-Cochrane and rapid reviews mentioned an a priori study protocol in contrast to all Cochrane reviews.ConclusionStakeholder engagement was not general practice, except for CRD reviews, although it was more common in rapid reviews. Reporting factors, such as including an a priori study protocol and a conflict of interest statement should be considered in conjunction with involving stakeholders.

Project description:BackgroundThere is evidence of geographical variation in the use of mental health services in the UK and in international settings. It is important to understand whether this variation reflects differences in the prevalence of mental disorders, or if there is evidence of variation related to other factors, such as population socioeconomic status and access to primary care services.MethodsThis is a cross-sectional ecological study using Public Health England data. The unit of analysis was the population served by clinical commissioning groups (CCGs), National Health Service (NHS) catchment areas. The analysis explored associations between area characteristics and the number of people in contact with mental health services using regression modelling. Explanatory variables included age, gender, prevalence of severe mental illness (SMI), prevalence of common mental disorder (CMD), index of multiple deprivation (IMD), unemployment, proportion of the population who are Black and Minority Ethnic (BAME), population density, access to and recovery in primary care psychological therapies. Unadjusted results are reported, as well as estimates adjusted for age, prevalence of CMD and prevalence of SMI.ResultsThe populations of 194 CCGs were included, clustered within 62 trusts (NHS providers of mental health services). The number of people in contact with mental health services showed wide variation by area (range from 1131 to 5205 per 100,000 population). Unemployment (adjusted IRR 1.11; 95% CI 1.05 to 1.17; p < 0.001) and deprivation (adjusted IRR 1.02 95% CI 1.01 to 1.04; p < 0.001) were associated with more people being in contact with mental health services. Areas with a higher proportion of the population who are BAME (IRR 0.95 95% CI 0.92 to 0.99 p = 0.007) had lower service use per 100,000 population. There was no evidence for association with access to primary care psychological therapies.ConclusionsThere is substantial variation in the use of mental health services by area of England. Social factors including deprivation, unemployment and population ethnicity continued to be associated with the outcome after controlling for the prevalence of mental illness. This suggests that there are factors that influence the local population use of mental health services in addition to the prevalence of mental disorder.

Project description:PurposeThis study is a scoping review of the different methods used to measure rurality in the health services research (HSR) literature.MethodsWe identified peer-reviewed empirical studies from 2010-2020 from seven leading HSR journals, including the Journal of Rural Health, that used any definition to measure rurality as a part of their analysis. From each study, we identified the geographic unit (e.g., county, zip code) and definition (e.g., Rural Urban Continuum Codes, Rural Urban Commuting Areas) used to classify categories of rurality. We analyzed whether geographic units and definitions used to classify rurality differed by focus area of studies, including costs, quality, and access to care. Lastly, we examined the number of rural categories used by authors to assess rural areas.FindingsIn 103 included studies, five different geographic units and 11 definitions were used to measure rurality. The most common geographic units used to measure rurality were county (n = 59, 57%), which was used most frequently in studies examining cost (n = 12, 75%) and access (n = 33, 57.9%). Rural Urban Commuting Area codes were the most common definition used to measure rurality for studies examining access (n = 13, 22.8%) and quality (n = 10, 44%). The majority of included studies made rural versus urban comparisons (n = 82, 80%) as opposed to focusing on rural populations only (n = 21, 20%). Among studies that compared rural and urban populations, most studies used only one category to identify rural locations (n = 49 of 82 studies, 60%).ConclusionGeographic units and definitions to determine rurality were used inconsistently within and across studies with an HSR focus. This finding may affect how health disparities by rural location are determined and thus how resources and federal funds are allocated. Future research should focus on developing a standardized system to determine under what circumstances researchers should use different geographic units and methods to determine rurality by HSR focus area.

Project description:ObjectiveTo determine the contextual factors influencing research and research capacity building in rural health settings.DesignQualitative study using semi-structured telephone interviews to collect data regarding health professionals' research education and capacity building. Analysis involved inductive coding using Braun and Clark's thematic analysis; and deductive mapping to the Consolidated Framework for Implementation Research (CFIR).SettingVictorian rural health services and university campuses.ParticipantsTwenty senior rural health managers, academics and/or research coordinators. Participants had at least three years' experience in rural public health, health-related research or health education settings.Main outcome measuresContextual factors influencing the operationalisation and prioritisation of research capacity building in rural health services.ResultsFindings reflected the CFIR domains and constructs: intervention characteristics (relative advantage); outer setting (cosmopolitanism, external policies and incentives); inner setting (implementation climate, readiness for implementation); characteristics of individuals (self-efficacy); and process (planning, engaging). Findings illustrated the implementation context and the complex contextual tensions, which either prevent or enhance research capacity building in rural health services.ConclusionsRealising the Australian Government's vision for improved health service provision and health outcomes in rural areas requires a strong culture of research and research capacity building in rural health services. Low levels of rural research funding, chronic workforce shortages and the tension between undertaking research and delivering health care, all significantly impact the operationalisation and prioritisation of research capacity building in rural health services. Effective policy and investment addressing these contextual factors is crucial for the success of research capacity building in rural health services.

Dataset Information

Is there much variation in variation? Revisiting statistics of small area variation in health services research.

Publications

Is there much variation in variation? Revisiting statistics of small area variation in health services research.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets