470
views
0
recommends
+1 Recommend
0 collections
    24
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Metaprop: a Stata command to perform meta-analysis of binomial data

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Background

          Meta-analyses have become an essential tool in synthesizing evidence on clinical and epidemiological questions derived from a multitude of similar studies assessing the particular issue. Appropriate and accessible statistical software is needed to produce the summary statistic of interest.

          Methods

          Metaprop is a statistical program implemented to perform meta-analyses of proportions in Stata. It builds further on the existing Stata procedure metan which is typically used to pool effects (risk ratios, odds ratios, differences of risks or means) but which is also used to pool proportions. Metaprop implements procedures which are specific to binomial data and allows computation of exact binomial and score test-based confidence intervals. It provides appropriate methods for dealing with proportions close to or at the margins where the normal approximation procedures often break down, by use of the binomial distribution to model the within-study variability or by allowing Freeman-Tukey double arcsine transformation to stabilize the variances. Metaprop was applied on two published meta-analyses: 1) prevalence of HPV-infection in women with a Pap smear showing ASC-US; 2) cure rate after treatment for cervical precancer using cold coagulation.

          Results

          The first meta-analysis showed a pooled HPV-prevalence of 43% (95% CI: 38%-48%). In the second meta-analysis, the pooled percentage of cured women was 94% (95% CI: 86%-97%).

          Conclusion

          By using metaprop, no studies with 0% or 100% proportions were excluded from the meta-analysis. Furthermore, study specific and pooled confidence intervals always were within admissible values, contrary to the original publication, where metan was used.

          Related collections

          Most cited references15

          • Record: found
          • Abstract: not found
          • Article: not found

          THE USE OF CONFIDENCE OR FIDUCIAL LIMITS ILLUSTRATED IN THE CASE OF THE BINOMIAL

            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            Evidence regarding human papillomavirus testing in secondary prevention of cervical cancer.

            More than ever, clinicians need regularly updated reviews given the continuously increasing amount of new information regarding innovative cervical cancer prevention methods. A summary is given from recent meta-analyses and systematic reviews on 3 possible clinical applications of human papillomavirus (HPV) testing: triage of women with equivocal or low-grade cytologic abnormalities; prediction of the therapeutic outcome after treatment of cervical intraepithelial neoplasia (CIN) lesions, and last not but not least, primary screening for cervical cancer and pre-cancer. Consistent evidence is available indicating that HPV-triage with the Hybrid Capture(®) 2 assay (Qiagen Gaithersburg, Inc., MD, USA [previously Digene Corp.] (HC2) is more accurate (higher sensitivity, similar specificity) than repeat cytology to triage women with equivocal Pap smear results. Several other tests show at least similar accuracy but mRNA testing with the APTIMA(®) (Gen-Probe Inc., San Diego, CA, USA) test is similarly sensitive but more specific compared to HC2. In triage of low-grade squamous intraepithelial lesions (LSIL), HC2 is more sensitive but its specificity is substantially lower compared to repeat cytology. The APTIMA(®) test is more specific than HC2 without showing a loss in sensitivity. Identification of DNA of HPV types 16 and/or 18, or RNA from the five most carcinogenic HPV types allow selecting women at highest risk for CIN3+ but the sensitivity and negative predictive value of these markers are lower than full-range high-risk HPV (hrHPV) testing. After conservative treatment of cervical pre-cancer, HPV testing picks up more quickly, with higher sensitivity and not lower specificity, residual or recurrent high-grade CIN than follow-up cytology. Primary screening for hrHPV generally detects more CIN2, CIN3 or cancer compared to cytology at cut-off atypical squamous cells of undetermined significance (ASC-US) or LSIL, but is less specific. Combined HPV and cytology screening provides a further small gain in sensitivity at the expense of a considerable loss in specificity if positive by either test is referred to colposcopy, in comparison with HPV testing only. Randomised trials and follow-up of cohort studies consistently demonstrate a significantly lower cumulative incidence of CIN3+ and even of cancer, in women aged 30 years or older, who were at enrollment hrHPV DNA negative compared to those who were cytologically negative. The difference in cumulative risk of CIN3+ or cancer for double negative (cytology & HPV) versus only HPV-negative women is small. HC2, GP5+/6+ PCR (polymerase chain reaction), cobas(®) 4800 PCR (Roche Molecular Systems Inc., Alameda, CA, USA) and Real Time PCR (Abbott Molecular, Des Plaines, IL, USA) can be considered as clinically validated for use in primary screening. The loss in specificity associated with primary HPV-based screening can be compensated by appropriate algorithms involving reflex cytology and/or HPV genotyping for HPV16 or 18. There exists a substantial evidence base to support that HPV testing is advantageous both in triage of women with equivocal abnormal cytology, in surveillance after treatment of CIN lesions and in primary screening of women aged 30 years or older. However, the possible advantages offered by HPV-based screening require a well organised program with good compliance with screening and triage policies. This article forms part of a special supplement entitled "Comprehensive Control of HPV Infections and Related Diseases" Vaccine Volume 30, Supplement 5, 2012. Copyright © 2012 Marc Arbyn. Published by Elsevier Ltd.. All rights reserved.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              The binomial distribution of meta-analysis was preferred to model within-study variability.

              When studies report proportions such as sensitivity or specificity, it is customary to meta-analyze them using the DerSimonian and Laird random effects model. This method approximates the within-study variability of the proportion by a normal distribution, which may lead to bias for several reasons. Alternatively an exact likelihood approach based on the binomial within-study distribution can be used. This method can easily be performed in standard statistical packages. We investigate the performance of the standard method and the alternative approach. We compare the two approaches through a simulation study, in terms of bias, mean-squared error, and coverage probabilities. We varied the size of the overall sensitivity or specificity, the between-studies variance, the within-study sample sizes, and the number of studies. The methods are illustrated using a published meta-analysis data set. The exact likelihood approach performs always better than the approximate approach and gives unbiased estimates. The coverage probability, in particular for the profile likelihood, is also reasonably acceptable. In contrast, the approximate approach gives huge bias with very poor coverage probability in many cases. The exact likelihood approach is the method of preference and should be used whenever feasible.
                Bookmark

                Author and article information

                Contributors
                Victoria.NyawiraNyaga@wiv-isp.be
                Marc.Arbyn@wiv-isp.be
                marc.aerts@uhasselt.be
                Journal
                Arch Public Health
                Arch Public Health
                Archives of Public Health
                BioMed Central (London )
                0778-7367
                2049-3258
                10 November 2014
                2014
                : 72
                : 1
                : 39
                Affiliations
                [ ]Unit of Cancer Epidemiology, Scientific Institute of Public Health, Juliette Wytsmanstraat 14, 1050 Brussels, Belgium
                [ ]Center for Statistics, Hasselt University, Agoralaan Building D, 3590 Diepenbeek, Belgium
                Article
                5060
                10.1186/2049-3258-72-39
                4373114
                25810908
                5ca7e743-ff88-430f-baf0-cfcad884ef67
                © Nyaga et al.; licensee BioMed Central Ltd. 2014

                This article is published under license to BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License ( http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly credited. The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated.

                History
                : 5 May 2014
                : 11 July 2014
                Categories
                Methodology
                Custom metadata
                © The Author(s) 2014

                Public health
                meta-analysis,stata,binomial,logistic-normal,confidence intervals,freeman-tukey double arcsine transformation

                Comments

                Comment on this article