Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2021 Jan 30;70(5):1015–1032. doi: 10.1093/sysbio/syab004

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

© The Author(s) 2021. Published by Oxford University Press, on behalf of the Society of Systematic Biologists.

This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is properly cited. For commercialre-use, please contact journals.permissions@oup.com

PMC Copyright notice

Figure 9. — Relative performance gains on empirical data sets using the naive mixture with MC as reference. a) The percentage of runs having succeeded to converge within 10 million iterations. b) and c) The acceleration in convergence time before and after removal of the burnin phase, respectively. Convergence thresholds were fixed to a 2% and 1% average error per split. Panels d) and e) report increases in C-V efficiency and coverage. b), c) and d) are weighted by the relative runtime shown in Figure S18 of the Supplementary material available on Dryad. Absolute values are available in Figure S17 of the Supplementary material available on Dryad.

Inline graphic — Relative performance gains on empirical data sets using the naive mixture with MC as reference. a) The percentage of runs having succeeded to converge within 10 million iterations. b) and c) The acceleration in convergence time before and after removal of the burnin phase, respectively. Convergence thresholds were fixed to a 2% and 1% average error per split. Panels d) and e) report increases in C-V efficiency and coverage. b), c) and d) are weighted by the relative runtime shown in Figure S18 of the Supplementary material available on Dryad. Absolute values are available in Figure S17 of the Supplementary material available on Dryad.