skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Comparing traditional and Bayesian approaches to ecological meta‐analysis
1. Despite the wide application of meta-analysis in ecology, some of the traditional methods used for meta-analysis may not perform well given the type of data characteristic of ecological meta-analyses. 2. We reviewed published meta-analyses on the ecological impacts of global climate change, evaluating the number of replicates used in the primary studies (𝑛𝑖) and the number of studies or records (k) that were aggregated to calculate a mean effect size. We used the results of the review in a simulation experiment to assess the performance of conventional frequentist and Bayesian meta-analysis methods for estimating a mean effect size and its uncertainty interval. 3. Our literature review showed that 𝑛𝑖 and k were highly variable, distributions were rightskewed, and were generally small (median 𝑛𝑖 =5, median k=44). Our simulations show that the choice of method for calculating uncertainty intervals was critical for obtaining appropriate coverage (close to the nominal value of 0.95). When k was low (<40), 95% coverage was achieved by a confidence interval based on the t-distribution that uses an adjusted standard error (the Hartung-Knapp-Sidik-Jonkman, HKSJ), or by a Bayesian credible interval, whereas bootstrap or z-distribution confidence intervals had lower coverage. Despite the importance of the method to calculate the uncertainty interval, 39% of the meta-analyses reviewed did not report the method used, and of the 61% that did, 94% used a potentially problematic method, which may be a consequence of software defaults. 4. In general, for a simple random-effects meta-analysis, the performance of the best frequentist and Bayesian methods were similar for the same combinations of factors (k and mean replication), though the Bayesian approach had higher than nominal (>95%) coverage for the mean effect when k was very low (k<15). Our literature review suggests that many metaanalyses that used z-distribution or bootstrapping confidence intervals may have overestimated the statistical significance of their results when the number of studies was low; more appropriate methods need to be adopted in ecological meta-analyses.  more » « less
Award ID(s):
1655394 1655426
PAR ID:
10170259
Author(s) / Creator(s):
; ; ; ; ;
Date Published:
Journal Name:
Methods in Ecology and Evolution
ISSN:
2041-210X
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; (, Molecular Biology and Evolution)
    Su, Bing (Ed.)
    Abstract Confidence intervals (CIs) depict the statistical uncertainty surrounding evolutionary divergence time estimates. They capture variance contributed by the finite number of sequences and sites used in the alignment, deviations of evolutionary rates from a strict molecular clock in a phylogeny, and uncertainty associated with clock calibrations. Reliable tests of biological hypotheses demand reliable CIs. However, current non-Bayesian methods may produce unreliable CIs because they do not incorporate rate variation among lineages and interactions among clock calibrations properly. Here, we present a new analytical method to calculate CIs of divergence times estimated using the RelTime method, along with an approach to utilize multiple calibration uncertainty densities in dating analyses. Empirical data analyses showed that the new methods produce CIs that overlap with Bayesian highest posterior density intervals. In the analysis of computer-simulated data, we found that RelTime CIs show excellent average coverage probabilities, that is, the actual time is contained within the CIs with a 94% probability. These developments will encourage broader use of computationally efficient RelTime approaches in molecular dating analyses and biological hypothesis testing. 
    more » « less
  2. ; ; (, Statistical Analysis and Data Mining: The ASA Data Science Journal)
    Abstract In many scientific experiments, multiarmed bandits are used as an adaptive data collection method. However, this adaptive process can lead to a dependence that renders many commonly used statistical inference methods invalid. An example of this is the sample mean, which is a natural estimator of the mean parameter but can be biased. This can cause test statistics based on this estimator to have an inflated type I error rate, and the resulting confidence intervals may have significantly lower coverage probabilities than their nominal values. To address this issue, we propose an alternative approach called randomized multiarm bandits (rMAB). This combines a randomization step with a chosen MAB algorithm, and by selecting the randomization probability appropriately, optimal regret can be achieved asymptotically. Numerical evidence shows that the bias of the sample mean based on the rMAB is much smaller than that of other methods. The test statistic and confidence interval produced by this method also perform much better than its competitors. 
    more » « less
  3. ; ; ; ; ; ; ; ; ; ; et al (, Environmental Data Initiative)
    Transect-based monitoring has long been a valuable tool in ecosystem monitoring. These transects are often used to measure multiple ecosystem attributes. The line-point intercept (LPI), vegetation height, and canopy gap intercept methods comprise a set of core methods, which provide indicators of ecosystem condition. However, users struggle to design a sampling strategy that optimizes the ability to detect ecological change using transect-based methods. We assessed the sensitivity of these core methods on a one-hectare plot to transect length, number, and sampling interval to determine: 1) minimum sampling required to describe ecosystem characteristics and detect change for each method and 2) optimal transect length and number for all three methods to make recommendations for future analyses and monitoring efforts. We used data from 13 National Wind Erosion Research Network locations spanning the western US, which included 151 measurements over time across five biomes. We found that longer and increased numbers of transects were more important for reducing sampling error than increased sample intensity along transects. For all methods and indicators across plots, three 100-m transects reduced sampling error so that indicator estimates fall within an 95% confidence interval of +/- 5% for canopy gap intercept and LPI-total foliar cover, +/- 5 cm for height and +/- two species for LPI-species counts. For the same criteria at 80% confidence intervals, two 100-m transects are needed. Site-scale inference was strongly affected by sample design, consequently our understanding of ecological dynamics may be influenced by sampling decisions. 
    more » « less
  4. ; (, International Journal of Molecular Sciences)
    We compare several different methods to quantify the uncertainty of binding parameters estimated from isothermal titration calorimetry data: the asymptotic standard error from maximum likelihood estimation, error propagation based on a first-order Taylor series expansion, and the Bayesian credible interval. When the methods are applied to simulated experiments and to measurements of Mg(II) binding to EDTA, the asymptotic standard error underestimates the uncertainty in the free energy and enthalpy of binding. Error propagation overestimates the uncertainty for both quantities, except in the simulations, where it underestimates the uncertainty of enthalpy for confidence intervals less than 70%. In both datasets, Bayesian credible intervals are much closer to observed confidence intervals. 
    more » « less
  5. ; ; ; ; ; ; ; ; ; ; et al (, Eurosurveillance)
    null (Ed.)
    Background The natural history of disease in patients infected with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) remained obscure during the early pandemic. Aim Our objective was to estimate epidemiological parameters of coronavirus disease (COVID-19) and assess the relative infectivity of the incubation period. Methods We estimated the distributions of four epidemiological parameters of SARS-CoV-2 transmission using a large database of COVID-19 cases and potential transmission pairs of cases, and assessed their heterogeneity by demographics, epidemic phase and geographical region. We further calculated the time of peak infectivity and quantified the proportion of secondary infections during the incubation period. Results The median incubation period was 7.2 (95% confidence interval (CI): 6.9‒7.5) days. The median serial and generation intervals were similar, 4.7 (95% CI: 4.2‒5.3) and 4.6 (95% CI: 4.2‒5.1) days, respectively. Paediatric cases < 18 years had a longer incubation period than adult age groups (p = 0.007). The median incubation period increased from 4.4 days before 25 January to 11.5 days after 31 January (p < 0.001), whereas the median serial (generation) interval contracted from 5.9 (4.8) days before 25 January to 3.4 (3.7) days after. The median time from symptom onset to discharge was also shortened from 18.3 before 22 January to 14.1 days after. Peak infectivity occurred 1 day before symptom onset on average, and the incubation period accounted for 70% of transmission. Conclusion The high infectivity during the incubation period led to short generation and serial intervals, necessitating aggressive control measures such as early case finding and quarantine of close contacts. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Text Encoded Conversion
  • XML
  • Save / Share this Record
  • Send to Email