Skip to main content
Figure 1 | BMC Bioinformatics

Figure 1

From: A semi-nonparametric mixture model for selecting functionally consistent proteins

Figure 1

Power results for nine simulation settings. Schwartz Bayesian Information Criterion (BIC) provides the model selection criterion. Data were simulated under nine semi-nonparametric (SNP) mixture distributions with the tuning parameter K taking values 0, 1, or 2 for each SNP density. Sample sizes are 50, 100, 300, or 500. λ0 is 0.2, 0.5, or 0.8. The distance between the means of the component distributions is D and has values of 1 or 2. Power was calculated as the proportion of correctly rejected hypothesis for 1000 simulated data sets. Solid curves represent λ0 = 0.20 and D = 1() or D = 2(). Dashed curves represent λ0 = 0.50 and D = 1() or D = 2(). Dotted curves represent λ0 = 0.80 and D = 1() or D = 2().

Back to article page